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

    Neuronpedia

    INDEX
    Explanations

    relu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     testosterone
    -0.07
     enorm
    -0.06
     its
    -0.06
    การจ
    -0.06
    욱
    -0.06
     Salt
    -0.06
    zych
    -0.06
     tur
    -0.06
    Understanding
    -0.06
    006
    -0.06
    POSITIVE LOGITS
    orthy
    0.07
    DWORD
    0.07
     стил
    0.07
    .relu
    0.07
    relu
    0.07
     lumber
    0.06
    compass
    0.06
    払
    0.06
     строки
    0.06
    _portfolio
    0.06
    Act Density 0.001%

    No Known Activations