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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Written
    -0.08
    🎟
    -0.07
    �
    -0.07
    .Err
    -0.07
     vaccinations
    -0.07
    㟁
    -0.07
    .Nil
    -0.07
     ac
    -0.07
    ropsych
    -0.07
    _abstract
    -0.07
    POSITIVE LOGITS
    عرف
    0.09
    ────
    0.08
    rowData
    0.07
     pick
    0.06
     '(
    0.06
     })(
    0.06
     lights
    0.06
    );*/↵
    0.06
    swift
    0.06
    基地
    0.06
    Act Density 0.001%

    No Known Activations