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

    Neuronpedia

    INDEX
    Explanations

    due to and such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ៣
    0.61
     dukkham
    0.46
    ন
    0.46
    calup
    0.45
    జేపీ
    0.44
    followlike
    0.44
     gì
    0.44
     rupani
    0.44
    }$.
    0.44
    YS
    0.44
    POSITIVE LOGITS
    t
    0.58
     of
    0.53
    is
    0.47
     to
    0.46
    ,
    0.44
    ↵↵
    0.39
     is
    0.39
    "
    0.38
    ?
    0.38
     factorization
    0.36
    Act Density 0.289%

    No Known Activations