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

    Neuronpedia

    INDEX
    Explanations

    Code packages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MASK
    -0.07
     perse
    -0.06
    이자
    -0.06
    raman
    -0.06
     пут
    -0.06
     Schmidt
    -0.06
    -Muslim
    -0.06
    token
    -0.06
    الس
    -0.06
    empl
    -0.06
    POSITIVE LOGITS
    τει
    0.07
    asn
    0.07
    kre
    0.06
    eq
    0.06
     مش
    0.06
    开放
    0.06
     kişisel
    0.06
    obec
    0.06
     o
    0.06
     orgas
    0.06
    Act Density 0.022%

    No Known Activations