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

    Neuronpedia

    INDEX
    Explanations

    sharing personal stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "class
    -0.08
    Scaler
    -0.07
    为
    -0.07
    pii
    -0.06
     packets
    -0.06
     ankles
    -0.06
    птом
    -0.06
     pump
    -0.06
    เศษ
    -0.06
     tablet
    -0.06
    POSITIVE LOGITS
     proposition
    0.07
     MethodInvocation
    0.06
     oluyor
    0.06
     ensued
    0.06
    _already
    0.06
     /**<
    0.06
     Drain
    0.06
     onBlur
    0.06
    ík
    0.06
     cdr
    0.06
    Act Density 0.066%

    No Known Activations