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

    Neuronpedia

    INDEX
    Explanations

    surface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .API
    -0.07
    ла
    -0.07
    ._↵↵
    -0.07
    aku
    -0.06
    ometown
    -0.06
    icker
    -0.06
    IGHLIGHT
    -0.06
    nas
    -0.06
     przypad
    -0.06
     Path
    -0.06
    POSITIVE LOGITS
     oxidation
    0.07
     Hubbard
    0.07
    _customize
    0.06
    observ
    0.06
     screen
    0.06
     eben
    0.06
    sale
    0.06
    ुड
    0.06
    0.06
    び
    0.06
    Act Density 0.009%

    No Known Activations