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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experiences and sentiments

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

    Follows possessive pronouns (my, her, their)

    np_acts-logits-general · gemini-2.0-flash

    is one or useful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.66
    InitVars
    -0.61
    تقاوى
    -0.58
    AnchorStyles
    -0.56
    
    -0.56
     Мексичка
    -0.56
    popper
    -0.55
    stdc
    -0.54
    ConstraintMaker
    -0.54
     незавершена
    -0.53
    POSITIVE LOGITS
     definately
    0.74
     noqa
    0.68
     definitely
    0.66
    idać
    0.62
    definitely
    0.61
    Referințe
    0.60
     such
    0.56
     verdient
    0.55
     certainly
    0.55
     definitivamente
    0.54
    Act Density 0.164%

    No Known Activations