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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    оку
    -0.08
    .NORTH
    -0.07
     Giz
    -0.07
    .exe
    -0.06
    ♀
    -0.06
    они
    -0.06
     monet
    -0.06
    eve
    -0.06
    зі
    -0.06
    (codec
    -0.06
    POSITIVE LOGITS
    に向
    0.07
    ints
    0.06
    ibilities
    0.06
     politik
    0.06
    /'+
    0.06
    .bias
    0.06
     Resume
    0.06
    nom
    0.06
    _disabled
    0.06
    Customer
    0.06
    Act Density 0.033%

    No Known Activations