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

    Neuronpedia

    INDEX
    Explanations

    vectorstore index

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Excellency
    2.15
     crush
    2.03
    ્
    1.92
     לפי
    1.84
     Hanson
    1.81
    ್ಟ
    1.75
     Regards
    1.73
     intellect
    1.73
     combined
    1.73
    le
    1.72
    POSITIVE LOGITS
    е
    1.73
     wijze
    1.65
     traum
    1.64
     повышения
    1.61
     minutos
    1.60
     tasar
    1.56
     się
    1.54
     $("
    1.52
    ு
    1.51
    𝒎
    1.49
    Act Density 0.000%

    No Known Activations