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

    Neuronpedia

    INDEX
    Explanations

    code generation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    517
    -0.07
    195
    -0.06
     обмеж
    -0.06
    196
    -0.06
     Leisure
    -0.06
     بسی
    -0.06
    _unix
    -0.06
    olik
    -0.06
    _serial
    -0.06
    ----------↵↵
    -0.06
    POSITIVE LOGITS
     crashing
    0.08
     úda
    0.07
     durable
    0.07
    ]=[
    0.07
    game
    0.07
     adhere
    0.06
     horny
    0.06
    .Update
    0.06
    ic
    0.06
    dataArray
    0.06
    Act Density 0.004%

    No Known Activations