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

    Neuronpedia

    INDEX
    Explanations

    images

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     âg
    -0.08
     musée
    -0.08
    ensively
    -0.07
     klasik
    -0.07
    .firebaseio
    -0.07
     ruthless
    -0.07
     pagando
    -0.07
     antique
    -0.07
     teme
    -0.07
     limestone
    -0.07
    POSITIVE LOGITS
    无法
    0.09
     തര
    0.09
     cannot
    0.09
     Cannot
    0.09
     GPT
    0.09
     невозможно
    0.09
     outputs
    0.09
    Cannot
    0.08
    生成
    0.08
     can't
    0.08
    Act Density 0.018%

    No Known Activations