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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    our
    -0.09
    ours
    -0.09
    feature
    -0.08
    Seat
    -0.08
    define
    -0.08
     ihrer
    -0.08
    seat
    -0.08
    estimate
    -0.08
    restore
    -0.07
     article
    -0.07
    POSITIVE LOGITS
     شوي
    0.09
     questu
    0.08
     қойған
    0.08
     deterior
    0.08
    ")↵↵↵
    0.08
    ?>↵↵↵
    0.08
     בתוך
    0.08
     საფ
    0.08
     mwenye
    0.08
    "};↵↵
    0.08
    Act Density 0.000%

    No Known Activations