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

    Neuronpedia

    INDEX
    Explanations

    mathematical theorem or concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     serta
    1.60
     sambil
    1.55
     sapply
    1.52
     sebesar
    1.52
    য
    1.46
     ossia
    1.46
     powin
    1.46
     upay
    1.43
    SystemService
    1.43
     yani
    1.42
    POSITIVE LOGITS
    и
    1.78
    ка
    1.54
    esque
    1.52
    من
    1.47
    achusetts
    1.47
    న
    1.44
    ruary
    1.41
    राज्य
    1.37
    кон
    1.37
     전
    1.36
    Act Density 0.000%

    No Known Activations