Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific configurations, options, and conditions related to settings or features in software or technical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Aha: here is one catch" sentences

    np_acts-logits-general · gemini-2.0-flash

    cannot change or opt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fallu
    -0.37
     mattino
    -0.33
    vosť
    -0.32
     vainilla
    -0.31
    échelle
    -0.31
     Romains
    -0.31
     diffé
    -0.30
     diferencial
    -0.29
    notag
    -0.29
     especias
    -0.29
    POSITIVE LOGITS
     betweenstory
    0.73
    RegressionTest
    0.69
    səhifə
    0.63
     autorytatywna
    0.63
     Normdatei
    0.60
    حياته
    0.57
    Tikang
    0.56
     nahilalakip
    0.54
    enumii
    0.53
    SharedDtor
    0.52
    Act Density 0.820%

    No Known Activations