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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LANGUAGE
    -0.07
     giai
    -0.07
     Lazar
    -0.07
    coins
    -0.07
     فلس
    -0.06
    .fits
    -0.06
     nuru
    -0.06
     işlet
    -0.06
    adem
    -0.06
    spam
    -0.06
    POSITIVE LOGITS
     downright
    0.06
     设置
    0.06
    Producer
    0.06
     hikes
    0.06
    	rm
    0.06
    оки
    0.06
     �
    0.06
     уменьш
    0.06
     ()
    0.06
    erialized
    0.06
    Act Density 0.004%

    No Known Activations