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

    Neuronpedia

    INDEX
    Explanations

    underscore-prefixed or dash-separated terms in programming contexts

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

    code and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.64
    InjectAttribute
    -0.56
    SharedDtor
    -0.54
     Taktlose
    -0.52
    pushFollow
    -0.52
     مشين
    -0.51
     defStyleAttr
    -0.51
    bewerken
    -0.50
    ListItemIcon
    -0.50
     CommonModule
    -0.49
    POSITIVE LOGITS
     sacco
    0.47
     bankası
    0.45
    élaboration
    0.45
     kasarigan
    0.44
    SupportActionBar
    0.43
     hornear
    0.43
    corporated
    0.42
     대한
    0.42
     StringTokenizer
    0.42
    tagHelperRunner
    0.41
    Act Density 0.009%

    No Known Activations