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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (op
    -0.06
    (attribute
    -0.06
     smoothing
    -0.06
    ritic
    -0.06
     ano
    -0.06
    xed
    -0.06
    .createElement
    -0.06
     davon
    -0.06
     lined
    -0.06
    arse
    -0.05
    POSITIVE LOGITS
     Pistons
    0.07
    Music
    0.07
    .clientX
    0.07
    :Get
    0.07
     диаг
    0.07
     Laguna
    0.07
    ANTITY
    0.06
    _LICENSE
    0.06
    communications
    0.06
     которая
    0.06
    Act Density 0.001%

    No Known Activations