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

    Neuronpedia

    INDEX
    Explanations

    code structures and elements related to programming syntax

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

    network structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.96
     kasarigan
    -0.94
    NameInMap
    -0.84
     CreateTagHelper
    -0.82
    Rüyada
    -0.80
    GOTREF
    -0.76
    Autoritní
    -0.72
    WebVitals
    -0.72
    GEBURTSDATUM
    -0.71
    EDEFAULT
    -0.70
    POSITIVE LOGITS
     combined
    0.40
    sweise
    0.39
     would
    0.33
     https
    0.33
     significance
    0.32
     exactly
    0.32
    engesch
    0.32
     position
    0.32
     Regret
    0.31
     label
    0.31
    Act Density 0.112%

    No Known Activations