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

    Neuronpedia

    INDEX
    Explanations

    LaTeX package inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prototypical
    0.68
    ванне
    0.68
    OOSE
    0.67
     Data
    0.67
     protagonist
    0.65
     Datum
    0.65
     disturbance
    0.65
     povo
    0.64
     Daten
    0.64
     Dist
    0.64
    POSITIVE LOGITS
    lip
    0.72
    arxiv
    0.64
    float
    0.62
    graphicx
    0.60
     lip
    0.57
    rag
    0.54
    environ
    0.53
    array
    0.53
    alg
    0.53
    append
    0.52
    Act Density 0.002%

    No Known Activations