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

    Neuronpedia

    INDEX
    Explanations

    std::env

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    caused
    1.05
    el
    1.02
    phoneNumber
    0.97
    impact
    0.94
    ac
    0.92
    ceramic
    0.91
    occurring
    0.91
    mbox
    0.90
    ideal
    0.90
    initial
    0.89
    POSITIVE LOGITS
    تان
    1.02
    ТИ
    1.02
    טן
    0.99
     mediocr
    0.97
     bioinformatics
    0.97
    นะคะ
    0.93
    לים
    0.92
    ्ज
    0.91
     تاس
    0.90
     Bioinformatics
    0.90
    Act Density 0.001%

    No Known Activations