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
    -byte
    -0.07
     generating
    -0.07
    .er
    -0.07
     generate
    -0.07
    _diag
    -0.06
    -й
    -0.06
    对于
    -0.06
    wap
    -0.06
    _dist
    -0.06
     EFFECT
    -0.06
    POSITIVE LOGITS
     É
    0.06
    звичай
    0.06
    уш
    0.06
    Structured
    0.06
    .payload
    0.06
    shire
    0.06
     Vince
    0.06
    icity
    0.06
    劇
    0.06
     reservation
    0.06
    Act Density 0.013%

    No Known Activations