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

    Neuronpedia

    INDEX
    Explanations

    negative phrases and expressions related to uncertainty or difficulty

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

    Follows negative words

    np_acts-logits-general · gemini-2.0-flash

    not uncommon, no problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InitVars
    -0.80
     Мексичка
    -0.63
     nor
    -0.62
    Tikang
    -0.59
     HasFactory
    -0.58
     aimez
    -0.58
     AssemblyCompany
    -0.58
    ostante
    -0.57
    ViewImports
    -0.56
     efectivamente
    -0.55
    POSITIVE LOGITS
    ScopeManager
    0.63
    djangoproject
    0.56
    initComponents
    0.55
    不思議
    0.54
     objection
    0.53
     object
    0.53
     TOO
    0.53
     afterwards
    0.52
    orosi
    0.51
     принци
    0.51
    Act Density 0.210%

    No Known Activations