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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vice
    -0.08
     Australians
    -0.07
    /proto
    -0.07
     CentOS
    -0.07
    xbf
    -0.07
     mistr
    -0.07
    动漫
    -0.07
    Australian
    -0.07
    Accessor
    -0.06
    ㊜
    -0.06
    POSITIVE LOGITS
     Final
    0.07
    Reminder
    0.07
    fü
    0.07
    stitial
    0.07
    (if
    0.07
    ❯
    0.07
     disparities
    0.07
    睚
    0.06
     schwer
    0.06
    .handleChange
    0.06
    Act Density 0.001%

    No Known Activations