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

    Neuronpedia

    INDEX
    Explanations

    scale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    877
    -0.08
    吾
    -0.08
    868
    -0.08
    (no
    -0.07
     disappeared
    -0.07
     друж
    -0.07
     nab
    -0.07
    _input
    -0.07
    (inputStream
    -0.07
     thủ
    -0.07
    POSITIVE LOGITS
     scale
    0.15
     Scale
    0.14
     scales
    0.12
    Scale
    0.11
    scale
    0.11
    -scale
    0.10
     SCALE
    0.10
     scaling
    0.10
    cale
    0.09
    SCALE
    0.09
    Act Density 0.022%

    No Known Activations