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
     WAL
    -0.06
    bindings
    -0.06
     Každ
    -0.06
     Carbon
    -0.06
    악
    -0.06
    /N
    -0.06
    licenses
    -0.06
     Regression
    -0.06
    але
    -0.06
     Johns
    -0.05
    POSITIVE LOGITS
    .period
    0.07
    _index
    0.07
    _experiment
    0.07
    _avail
    0.07
     iz
    0.06
    .int
    0.06
    ...↵↵↵↵↵↵
    0.06
    ())↵↵↵
    0.06
    벨
    0.06
     Kinh
    0.06
    Act Density 0.004%

    No Known Activations