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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Contract
    0.73
    “.
    0.69
    ?“
    0.69
    ?’
    0.67
     Wasn
    0.65
     Earn
    0.63
    Man
    0.63
    Bună
    0.62
     बर्थडे
    0.61
    甭
    0.61
    POSITIVE LOGITS
     export
    0.79
     Export
    0.73
    export
    0.68
     exports
    0.66
     rele
    0.65
     exporting
    0.64
    导出
    0.62
    imes
    0.62
     /*
    0.61
     مض
    0.61
    Act Density 0.003%

    No Known Activations