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

    Neuronpedia

    INDEX
    Explanations

    Were you testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Products
    0.42
     exacerbate
    0.39
    pecific
    0.38
    Py
    0.37
     dissociate
    0.37
    Specific
    0.37
    Pharmac
    0.37
     ():
    0.36
     pharmac
    0.36
    カテゴリ
    0.36
    POSITIVE LOGITS
    泽
    0.48
     apes
    0.47
     ကြ
    0.45
     就是
    0.45
     المر
    0.41
    棫
    0.41
     modem
    0.41
     ape
    0.40
     досить
    0.40
     ट्रेड
    0.40
    Act Density 0.001%

    No Known Activations