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

    Neuronpedia

    INDEX
    Explanations

    code and technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ELEMENT
    -0.06
    ("[%
    -0.06
     subdued
    -0.06
     Mk
    -0.06
    _TWO
    -0.06
    _NR
    -0.06
    编
    -0.06
    pickup
    -0.06
    _TUN
    -0.06
     concludes
    -0.06
    POSITIVE LOGITS
     november
    0.06
    endoza
    0.06
    аз
    0.06
    =========↵
    0.06
    链接
    0.06
    _categoria
    0.06
     lc
    0.06
     sql
    0.06
    chedule
    0.06
     действительно
    0.06
    Act Density 0.033%

    No Known Activations