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

    Neuronpedia

    INDEX
    Explanations

    Code segments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .join
    -0.07
    уватися
    -0.07
    IH
    -0.07
    ımlar
    -0.07
    );
↵
    -0.06
     Girl
    -0.06
    iliz
    -0.06
    Concrete
    -0.06
     ｉ
    -0.06
     hlav
    -0.06
    POSITIVE LOGITS
    estring
    0.07
     precarious
    0.07
    enade
    0.07
    노
    0.06
    iffe
    0.06
    _LANE
    0.06
     Yorkers
    0.06
    -eff
    0.06
    -slider
    0.06
    .maxcdn
    0.06
    Act Density 0.010%

    No Known Activations