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

    Neuronpedia

    INDEX
    Explanations

    physics research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    끽
    -0.07
    Anal
    -0.07
     acct
    -0.07
    See
    -0.07
    供货
    -0.07
     Maduro
    -0.06
    stå
    -0.06
    �
    -0.06
    ḏ
    -0.06
    打ち
    -0.06
    POSITIVE LOGITS
    是否有
    0.08
     أيض
    0.07
    -door
    0.07
     fluoride
    0.07
     removing
    0.07
    好きな
    0.07
    ;j
    0.07
    ятся
    0.07
    Warning
    0.07
    入境
    0.07
    Act Density 0.006%

    No Known Activations