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

    Neuronpedia

    INDEX
    Explanations

    Ant

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ζη
    -0.07
    –↵↵
    -0.07
     rage
    -0.06
     oxy
    -0.06
    嗯
    -0.06
    े↵
    -0.06
     kh
    -0.06
     CCC
    -0.05
    чи
    -0.05
     Zoe
    -0.05
    POSITIVE LOGITS
    DED
    0.07
     Перед
    0.07
    ross
    0.06
    有什么
    0.06
    aud
    0.06
     hugged
    0.06
    anker
    0.06
    ś
    0.06
    iffies
    0.06
     мощ
    0.06
    Act Density 0.006%

    No Known Activations