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

    Neuronpedia

    INDEX
    Explanations

    Court of Appeal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brasili
    -0.78
     funcione
    -0.77
    annelse
    -0.74
    Humph
    -0.73
    ilt
    -0.73
     Ju
    -0.71
     QT
    -0.70
    anty
    -0.69
     work
    -0.69
     interess
    -0.69
    POSITIVE LOGITS
     Safely
    0.70
    Assignment
    0.70
    agai
    0.67
    pirazione
    0.67
    tembre
    0.67
    ഖ
    0.66
    BMC
    0.65
    jons
    0.65
     biztons
    0.65
     техні
    0.64
    Act Density 0.062%

    No Known Activations