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

    Neuronpedia

    INDEX
    Explanations

    Code dependencies and configurations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hackers
    -0.07
    aber
    -0.07
    .relu
    -0.07
    答复
    -0.07
    ified
    -0.07
    沱
    -0.07
    アウト
    -0.07
    ала
    -0.06
    ак
    -0.06
    少了
    -0.06
    POSITIVE LOGITS
    papers
    0.08
    CHE
    0.07
    珋
    0.07
    /em
    0.07
     counselling
    0.07
     MIN
    0.07
    眼部
    0.07
    ないように
    0.07
     payoff
    0.07
    ؽ
    0.06
    Act Density 0.004%

    No Known Activations