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

    Neuronpedia

    INDEX
    Explanations

    leadership positions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    중에
    -0.07
    alous
    -0.07
    Here
    -0.07
    索
    -0.07
     welcoming
    -0.07
    ,(
    -0.07
    itating
    -0.06
     Commerce
    -0.06
     mín
    -0.06
    olynomial
    -0.06
    POSITIVE LOGITS
     domácí
    0.07
    광역시
    0.06
     mdb
    0.06
    adratic
    0.06
    avel
    0.06
     Venezuel
    0.06
    aes
    0.06
    opens
    0.06
    oper
    0.06
    edik
    0.06
    Act Density 0.014%

    No Known Activations