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

    Neuronpedia

    INDEX
    Explanations

    make a name for yourself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.75
     .
    0.61
    ↵
    0.59
     placebo
    0.59
     Foi
    0.58
    us
    0.57
     :
    0.57
     fino
    0.56
     Festa
    0.55
     Kandid
    0.54
    POSITIVE LOGITS
    COLOG
    0.63
    ścic
    0.59
     ట
    0.57
    cored
    0.57
     город
    0.56
    𝒄
    0.55
    rystall
    0.55
    циони
    0.55
     टे
    0.54
    aic
    0.52
    Act Density 0.009%

    No Known Activations