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

    Neuronpedia

    INDEX
    Explanations

    writing an article about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    वर्ती
    1.23
    اتھن
    1.18
     spectrosc
    1.15
     terminology
    1.14
    んじゃない
    1.12
    ʦ
    1.12
    おります
    1.10
     DMSO
    1.08
    Obviously
    1.08
    时候
    1.08
    POSITIVE LOGITS
    published
    1.23
    を読む
    1.21
    бліоте
    1.20
    ted
    1.20
     đăng
    1.19
    en
    1.18
    档
    1.17
     published
    1.17
    νες
    1.15
     расходов
    1.15
    Act Density 0.025%

    No Known Activations