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

    Neuronpedia

    INDEX
    Explanations

    coordinates and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ğan
    -0.80
    образи
    -0.78
    Animated
    -0.73
    خره
    -0.73
     watershed
    -0.73
     acquisition
    -0.73
    ColumnInfo
    -0.72
    HttpStatusCode
    -0.72
     Sohn
    -0.72
     man
    -0.72
    POSITIVE LOGITS
     position
    1.35
    Position
    1.20
    position
    1.14
     positions
    1.13
     print
    1.09
     posição
    1.03
     paper
    1.00
    Units
    0.98
     posición
    0.98
     Position
    0.96
    Act Density 0.004%

    No Known Activations