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

    Neuronpedia

    INDEX
    Explanations

    autonomous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     continent
    -0.07
    ost
    -0.06
     album
    -0.06
    /bg
    -0.06
    prob
    -0.06
    Рµ
    -0.06
     valido
    -0.06
    祖
    -0.06
    產品
    -0.06
    UIAlertView
    -0.06
    POSITIVE LOGITS
    annah
    0.07
    Previously
    0.06
     TSR
    0.06
     independently
    0.06
    YG
    0.06
    огод
    0.06
     slime
    0.06
     Specification
    0.06
    .setHeight
    0.06
     Escorts
    0.06
    Act Density 0.011%

    No Known Activations