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

    Neuronpedia

    INDEX
    Explanations

    Technical/Academic text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    綜
    -0.07
     tang
    -0.07
    啕
    -0.06
    一起装修
    -0.06
     prick
    -0.06
     Dys
    -0.06
    иона
    -0.06
     Stores
    -0.06
    dx
    -0.06
     tops
    -0.06
    POSITIVE LOGITS
    constructor
    0.07
    配置
    0.07
    BUFFER
    0.07
     thresholds
    0.07
    .payload
    0.07
    饥饿
    0.07
    QPushButton
    0.07
    wheel
    0.07
     prejudices
    0.07
    红利
    0.07
    Act Density 0.000%

    No Known Activations