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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getActivity
    -0.07
    coding
    -0.07
    _ov
    -0.06
     WG
    -0.06
    (Config
    -0.06
     teas
    -0.06
     Zag
    -0.06
     dispatch
    -0.06
     زی
    -0.06
     CHK
    -0.06
    POSITIVE LOGITS
    ParameterValue
    0.07
    année
    0.06
    nost
    0.06
    ющей
    0.06
     courtesy
    0.06
    検
    0.06
    arParams
    0.06
    sono
    0.06
    CREEN
    0.06
    .DefaultCellStyle
    0.06
    Act Density 0.020%

    No Known Activations