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

    Neuronpedia

    INDEX
    Explanations

    occurrences of variables and their assignments in programming code

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

    list indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.89
     ſehr
    -0.81
    nodoc
    -0.79
    <pad>
    -0.79
    <unused51>
    -0.79
    <unused17>
    -0.79
    <unused42>
    -0.79
    <unused41>
    -0.79
    <unused8>
    -0.79
    <unused14>
    -0.79
    POSITIVE LOGITS
     copas
    0.38
    Autres
    0.34
    Others
    0.34
     jugement
    0.34
     Nación
    0.33
     Gubernur
    0.33
     Kerajaan
    0.32
     étoile
    0.32
     noël
    0.30
     Keuangan
    0.30
    Act Density 0.056%

    No Known Activations