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

    Neuronpedia

    INDEX
    Explanations

    font names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Н
    0.62
    Д
    0.59
    ن
    0.51
    antera
    0.46
    а
    0.46
    на
    0.45
    е
    0.45
    НА
    0.44
     çeşitli
    0.44
    न
    0.43
    POSITIVE LOGITS
    0.52
    عيه
    0.50
    listBox
    0.50
    oncé
    0.48
     chắn
    0.45
    0.45
     roam
    0.45
    crafted
    0.45
    tae
    0.45
    ură
    0.44
    Act Density 0.003%

    No Known Activations