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

    Neuronpedia

    INDEX
    Explanations

    now followed by english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     august
    0.41
    *
    0.41
    irte
    0.40
     powsta
    0.39
     molds
    0.38
    یکل
    0.37
    Prior
    0.36
     ಇದ
    0.36
     preparedness
    0.36
    flatable
    0.36
    POSITIVE LOGITS
    adays
    0.49
    ței
    0.44
    蒡
    0.44
     رحم
    0.43
    逄
    0.43
     какая
    0.42
     যেই
    0.41
    ής
    0.41
     veremos
    0.40
     مشغول
    0.40
    Act Density 0.000%

    No Known Activations