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

    Neuronpedia

    INDEX
    Explanations

    canvas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conquered
    -0.08
     celebrating
    -0.08
     Doğu
    -0.07
    [child
    -0.07
     western
    -0.07
    Classification
    -0.07
    parse
    -0.07
     state
    -0.07
    Wei
    -0.07
    Revision
    -0.06
    POSITIVE LOGITS
    อากาศ
    0.06
     GAM
    0.06
     okres
    0.05
    キャ
    0.05
    .amazonaws
    0.05
     Stopwatch
    0.05
     recreational
    0.05
    .getBounds
    0.05
     abort
    0.05
    推
    0.05
    Act Density 0.002%

    No Known Activations