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

    Neuronpedia

    INDEX
    Explanations

    standard library, output, input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.45
    ↵↵↵
    0.40
    单独
    0.39
    ING
    0.38
    慶
    0.38
    ké
    0.38
    एं
    0.37
    iken
    0.37
    <unused61>
    0.36
    rike
    0.36
    POSITIVE LOGITS
     Standard
    0.82
     표준
    0.82
    Standard
    0.75
    的标准
    0.70
     स्टैंडर्ड
    0.68
    标准
    0.68
     STANDARD
    0.66
    ндарт
    0.66
     標準
    0.65
    standard
    0.65
    Act Density 0.029%

    No Known Activations