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

    Neuronpedia

    INDEX
    Explanations

    variable or item identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     대부분
    0.81
     العديد
    0.80
     nahezu
    0.77
     ogrom
    0.77
     الكثير
    0.77
     schließlich
    0.74
    그리고
    0.72
    Michael
    0.72
    валось
    0.71
     menghadapi
    0.71
    POSITIVE LOGITS
    ifiably
    0.86
    ಕ್ತಿ
    0.80
    id
    0.77
    要
    0.77
     value
    0.76
    elementType
    0.76
    別
    0.75
    SPT
    0.75
    ێنی
    0.74
    ytics
    0.74
    Act Density 0.566%

    No Known Activations