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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rück
    -0.07
     Ginny
    -0.07
    标题
    -0.06
    Below
    -0.06
    middleware
    -0.06
    _ter
    -0.06
     stature
    -0.06
    せる
    -0.06
     Major
    -0.06
    _THIS
    -0.06
    POSITIVE LOGITS
     склад
    0.06
    .unsplash
    0.06
     ورزش
    0.06
    는다
    0.06
    usz
    0.06
    ,),
    0.06
     ballistic
    0.06
    魯
    0.06
    sendKeys
    0.06
    ricanes
    0.06
    Act Density 0.003%

    No Known Activations