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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OS
    -0.08
    كومة
    -0.07
     А
    -0.07
    ief
    -0.07
     infants
    -0.06
    -part
    -0.06
    edian
    -0.06
     diploma
    -0.06
     дир
    -0.06
    igans
    -0.06
    POSITIVE LOGITS
    _Struct
    0.06
     limiting
    0.06
    xDF
    0.06
     camb
    0.06
    _GPIO
    0.06
    _BAD
    0.06
    .apple
    0.05
    ères
    0.05
    .amazonaws
    0.05
    .Style
    0.05
    Act Density 0.011%

    No Known Activations