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

    Neuronpedia

    INDEX
    Explanations

    number of words required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的数据
    0.44
    ಿಸ್ಟ
    0.39
     محاض
    0.37
     ip
    0.36
     Abi
    0.36
    数据
    0.36
     getUserBy
    0.35
     abiotic
    0.35
    դ
    0.35
    κτήθηκε
    0.35
    POSITIVE LOGITS
    ровки
    0.39
    penas
    0.39
    끅
    0.39
     evanes
    0.38
    ^*(\
    0.38
     indis
    0.38
     ಮಾಡಲು
    0.38
    ELINE
    0.37
    XK
    0.37
    riya
    0.37
    Act Density 0.023%

    No Known Activations