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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paint
    -0.06
    εχ
    -0.06
     adidas
    -0.06
     fallen
    -0.06
    場合は
    -0.06
     hace
    -0.06
    eof
    -0.06
     anonymously
    -0.06
    iado
    -0.06
     baked
    -0.06
    POSITIVE LOGITS
    сим
    0.08
    _Profile
    0.07
    ानद
    0.07
    (iter
    0.06
     يون
    0.06
    �
    0.06
     İslam
    0.06
    ٬
    0.06
    .Observable
    0.06
    ylon
    0.06
    Act Density 0.003%

    No Known Activations