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

    Neuronpedia

    INDEX
    Explanations

    optimize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tarif
    -0.06
    /comment
    -0.06
     अलग
    -0.06
    	fr
    -0.06
     identified
    -0.06
     Sunrise
    -0.06
    -loader
    -0.06
    mıyor
    -0.06
     Cristina
    -0.06
     ترجم
    -0.06
    POSITIVE LOGITS
     mount
    0.07
     embark
    0.06
     curly
    0.06
    针
    0.06
    去
    0.06
    防
    0.06
    产生
    0.06
    [^
    0.06
     pys
    0.06
    ANC
    0.06
    Act Density 0.019%

    No Known Activations