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

    Neuronpedia

    INDEX
    Explanations

    phrases related to capability or limitation

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

    "cannot" or "can't"

    np_acts-logits-general · gemini-2.0-flash

    cannot be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bosity
    -0.51
    getChildAt
    -0.47
    ynia
    -0.47
    各样的
    -0.46
    upol
    -0.44
     Pingback
    -0.44
    なくても
    -0.43
    ticed
    -0.42
     occaf
    -0.42
     tvo
    -0.42
    POSITIVE LOGITS
     afford
    0.89
     raisonnable
    0.80
    ViewImports
    0.76
    ModelAdmin
    0.71
    Personendaten
    0.71
     realistically
    0.70
    TypedDataSet
    0.70
    verwijspagina
    0.69
     feas
    0.69
    MemoryWarning
    0.69
    Act Density 0.291%

    No Known Activations