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

    Neuronpedia

    INDEX
    Explanations

    predictions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    놉
    -0.08
    "These
    -0.07
     european
    -0.07
    白马
    -0.07
    受理
    -0.07
     Jaguar
    -0.07
     therap
    -0.06
     �
    -0.06
    랙
    -0.06
    丝绸之路
    -0.06
    POSITIVE LOGITS
     hmm
    0.08
    ′
    0.07
    ')}↵
    0.07
     Bund
    0.07
    珏
    0.07
    ሁ
    0.07
    稳固
    0.07
     Feeling
    0.07
    uhe
    0.07
     работает
    0.06
    Act Density 0.001%

    No Known Activations