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

    Neuronpedia

    INDEX
    Explanations

    Key concepts, structure, and relationship definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CaCO
    1.07
    ୟ
    1.04
     épaisse
    1.02
    いる
    1.02
     arqué
    0.97
     օ
    0.97
    िया
    0.96
    是个
    0.95
     Caedwalla
    0.95
     바랍니다
    0.93
    POSITIVE LOGITS
    ra
    0.93
    EL
    0.91
    ssä
    0.89
    ્સ
    0.84
    ts
    0.82
    िन
    0.82
    ten
    0.78
    rou
    0.77
    tidak
    0.77
     cor
    0.76
    Act Density 0.001%

    No Known Activations