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

    Neuronpedia

    INDEX
    Explanations

    -doc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     baseURL
    -0.08
     introducing
    -0.08
    (b
    -0.07
    coverage
    -0.07
     NotificationCenter
    -0.07
    瑱
    -0.07
    빗
    -0.07
    サービ
    -0.07
     gev
    -0.07
     masturbating
    -0.07
    POSITIVE LOGITS
    延误
    0.07
     Something
    0.07
    ↵      ↵
    0.07
        
    0.07
    机能
    0.07
    ѿ
    0.07
     greater
    0.07
    Bindable
    0.07
    炼
    0.07
    效果
    0.07
    Act Density 0.000%

    No Known Activations