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

    Neuronpedia

    INDEX
    Explanations

    AssemblyProduct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rentices
    -0.85
    ratulations
    -0.83
    copg
    -0.83
    cense
    -0.82
    requestCode
    -0.82
    cognito
    -0.79
    utives
    -0.78
    nessed
    -0.78
    LEncoder
    -0.78
    PLIES
    -0.77
    POSITIVE LOGITS
    out
    0.69
    s
    0.66
    da
    0.65
    ValueStyle
    0.59
    sv
    0.58
    sw
    0.58
    ly
    0.57
    mat
    0.57
    ira
    0.56
    sn
    0.56
    Act Density 0.048%

    No Known Activations