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

    Neuronpedia

    INDEX
    Explanations

    numeric values and references to specific years or quantities in a historical context

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

    years after "In"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.63
    PerformLayout
    -0.56
    ValueStyle
    -0.54
     typelib
    -0.53
    imageshack
    -0.53
     CallOverrides
    -0.51
     arşivlendi
    -0.51
    printStackTrace
    -0.49
    chyma
    -0.49
    клопе
    -0.48
    POSITIVE LOGITS
     uſed
    0.38
     raiſ
    0.37
    Soon
    0.36
     Soon
    0.36
    HideInInspector
    0.35
     stiker
    0.34
     parís
    0.34
     soja
    0.34
    apimachinery
    0.33
     Shortly
    0.33
    Act Density 0.030%

    No Known Activations