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
    ské
    -0.06
     多
    -0.06
    ěstí
    -0.06
    ovanou
    -0.06
    ulur
    -0.06
    وير
    -0.06
    غيرة
    -0.06
    ๕
    -0.06
    フ�
    -0.06
     olds
    -0.06
    POSITIVE LOGITS
    skirts
    0.07
    constructed
    0.07
    Picture
    0.07
    toggle
    0.07
     EventHandler
    0.06
    	prev
    0.06
     justify
    0.06
     Listen
    0.06
    Wallet
    0.06
     haya
    0.06
    Act Density 0.000%

    No Known Activations