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

    Neuronpedia

    INDEX
    Explanations

    research-related terminology and expressions of study objectives

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

    research aims and hypotheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $}}
    -0.45
    SpringBootTest
    -0.44
     tartalomajánló
    -0.43
    messageInfo
    -0.43
    UVWXYZ
    -0.42
     Cep
    -0.41
     NgModule
    -0.41
     thun
    -0.41
     Awesome
    -0.41
     kaarangay
    -0.40
    POSITIVE LOGITS
    transQ
    0.57
    LabelTagHelper
    0.54
     fallu
    0.47
     Khusus
    0.46
     amaç
    0.46
     Kecil
    0.46
     <<<<<<<<<<<<<<
    0.46
     kysy
    0.45
     tarko
    0.45
     konkre
    0.45
    Act Density 0.043%

    No Known Activations