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

    Neuronpedia

    INDEX
    Explanations

    paying homage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     promoters
    -0.07
    adf
    -0.07
    继
    -0.07
     conducive
    -0.07
     ту
    -0.06
    Foto
    -0.06
     chatt
    -0.06
     skill
    -0.06
    Salt
    -0.06
    струмент
    -0.06
    POSITIVE LOGITS
     NSStringFromClass
    0.07
     Unsafe
    0.06
     rezerv
    0.06
     revision
    0.06
    _tf
    0.06
    lasting
    0.06
    _cod
    0.06
     ↵↵
    0.06
    ...,
    0.06
     appetite
    0.06
    Act Density 0.095%

    No Known Activations