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

    Neuronpedia

    INDEX
    Explanations

    project/package/file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    strcpy
    0.74
    frac
    0.73
    countries
    0.71
     swo
    0.71
    polygon
    0.70
     су
    0.70
    bpy
    0.70
    aol
    0.68
    indx
    0.67
     [
    0.66
    POSITIVE LOGITS
    nextToken
    0.84
     acumen
    0.83
    וא
    0.82
    様専用
    0.80
     équipé
    0.79
     filho
    0.79
    崽
    0.79
     अकेला
    0.79
     apartamento
    0.79
    <unused467>
    0.79
    Act Density 0.007%

    No Known Activations