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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    眢
    -0.07
     Для
    -0.07
    lement
    -0.07
    [q
    -0.07
     setTimeout
    -0.06
     prevailed
    -0.06
    不太好
    -0.06
    ⤴
    -0.06
    ope
    -0.06
    >s
    -0.06
    POSITIVE LOGITS
     coursework
    0.07
    缺陷
    0.07
     alkal
    0.07
    몰
    0.07
     comparable
    0.07
     forth
    0.07
    唇
    0.07
    ᶦ
    0.06
    分别是
    0.06
    (numbers
    0.06
    Act Density 0.109%

    No Known Activations