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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     שלי
    -0.07
     meld
    -0.07
    身后
    -0.07
    ası
    -0.06
     discovered
    -0.06
     artificially
    -0.06
     flowing
    -0.06
    _Profile
    -0.06
     loạt
    -0.06
     nội
    -0.06
    POSITIVE LOGITS
    ook
    0.07
     digital
    0.07
    杌
    0.07
     conduct
    0.07
     October
    0.06
     disease
    0.06
    """↵
    0.06
    鳡
    0.06
    wallet
    0.06
    ?url
    0.06
    Act Density 0.056%

    No Known Activations