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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umberland
    -0.07
     Neue
    -0.06
     phút
    -0.06
     kamu
    -0.06
    rup
    -0.06
    	model
    -0.06
    Almost
    -0.06
    ulan
    -0.06
    นเต
    -0.06
     deber
    -0.06
    POSITIVE LOGITS
    ‌ها
    0.07
     इसस
    0.06
    .YesNo
    0.06
    ابل
    0.06
    ＊
    0.06
    能力
    0.06
     Hearth
    0.06
    WSC
    0.06
    경기
    0.05
     OnCollision
    0.05
    Act Density 0.019%

    No Known Activations