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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Den
    -0.07
     avi
    -0.07
    flater
    -0.06
     İslam
    -0.06
    venida
    -0.06
     Yüz
    -0.06
     рівня
    -0.06
     　
    -0.06
    annel
    -0.06
    astr
    -0.06
    POSITIVE LOGITS
     oath
    0.07
    vit
    0.07
     shuts
    0.06
    	search
    0.06
     thải
    0.06
     tire
    0.06
    (nextProps
    0.06
     Evaluation
    0.06
     kys
    0.06
     Kingston
    0.06
    Act Density 0.015%

    No Known Activations