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

    Neuronpedia

    INDEX
    Explanations

    permissions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⓚ
    -0.07
    🖊
    -0.07
    专注于
    -0.07
     Pg
    -0.07
    围棋
    -0.06
     unprecedented
    -0.06
    .CreateInstance
    -0.06
    letic
    -0.06
    ծ
    -0.06
     lĩnh
    -0.06
    POSITIVE LOGITS
    Roll
    0.07
    Grey
    0.07
     recur
    0.07
    mort
    0.06
     alignments
    0.06
    nost
    0.06
    测试
    0.06
    (core
    0.06
    发送
    0.06
     accusation
    0.06
    Act Density 0.003%

    No Known Activations