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

    Neuronpedia

    INDEX
    Explanations

    Technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Inland
    -0.08
    елик
    -0.08
    Packing
    -0.08
     bestuurs
    -0.08
     ámbitos
    -0.07
     Abroad
    -0.07
     seams
    -0.07
     Sall
    -0.07
     ámbito
    -0.07
    極
    -0.07
    POSITIVE LOGITS
    智能
    0.08
    িএ
    0.08
     escolha
    0.08
    电影网站
    0.08
     সক্ষম
    0.08
    াঝ
    0.07
     g
    0.07
     настрой
    0.07
    য়
    0.07
    য়া
    0.07
    Act Density 0.073%

    No Known Activations