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

    Neuronpedia

    INDEX
    Explanations

    Removal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     impair
    -0.07
     phong
    -0.07
     discrete
    -0.07
    Раз
    -0.06
     entr
    -0.06
     Νο
    -0.06
    Você
    -0.06
    Iran
    -0.06
     vå
    -0.06
    MEM
    -0.06
    POSITIVE LOGITS
    거리
    0.08
    .NODE
    0.07
    .band
    0.06
     Ale
    0.06
    BOOLE
    0.06
    etailed
    0.06
    _predict
    0.06
    (instance
    0.06
     dataSize
    0.06
     Provid
    0.06
    Act Density 0.007%

    No Known Activations