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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ASURE
    -0.07
     IR
    -0.07
     organisations
    -0.07
     organizations
    -0.07
     wavelengths
    -0.06
    _interaction
    -0.06
     المهنة
    -0.06
    gne
    -0.06
    esso
    -0.06
     regardless
    -0.06
    POSITIVE LOGITS
     것도
    0.07
     bü
    0.06
    ="{!!
    0.06
     pioneered
    0.06
     밝
    0.06
     Conte
    0.06
    王
    0.06
    _ipv
    0.06
     Seah
    0.06
    ой
    0.06
    Act Density 0.022%

    No Known Activations