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

    Neuronpedia

    INDEX
    Explanations

    instructions and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CID
    -0.08
    ph
    -0.07
     nobody
    -0.06
    差
    -0.06
    ़न
    -0.06
    賀
    -0.06
     Role
    -0.06
    成员
    -0.06
     desta
    -0.06
    आर
    -0.06
    POSITIVE LOGITS
     Sioux
    0.06
    /resources
    0.06
     الب
    0.06
     इसक
    0.06
     उसक
    0.06
    lığa
    0.06
    _rates
    0.06
    .one
    0.06
    тив
    0.06
    mn
    0.06
    Act Density 0.000%

    No Known Activations