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

    Neuronpedia

    INDEX
    Explanations

    GeForce RTX

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ủi
    0.54
     vijj
    0.53
    сно
    0.52
    eliti
    0.52
     अन्य
    0.51
    żą
    0.51
     الأخرى
    0.51
     Более
    0.51
     અન્ય
    0.50
    więks
    0.50
    POSITIVE LOGITS
     they
    0.75
    ,
    0.71
     that
    0.70
     their
    0.70
    .
    0.69
     the
    0.68
     a
    0.67
     our
    0.63
     it
    0.63
     she
    0.57
    Act Density 0.230%

    No Known Activations