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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     त्या
    -0.09
     Drew
    -0.08
    Determ
    -0.08
     aquelas
    -0.08
     ákve
    -0.08
    Infrastructure
    -0.08
    ામ
    -0.07
    _INTEGER
    -0.07
     calculates
    -0.07
     bestimmen
    -0.07
    POSITIVE LOGITS
     teens
    0.09
     quir
    0.09
     sara
    0.09
    rais
    0.08
     septembre
    0.08
     Pocket
    0.08
    olda
    0.08
     WIFI
    0.08
     начина
    0.08
     Weird
    0.08
    Act Density 0.001%

    No Known Activations