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

    Neuronpedia

    INDEX
    Explanations

    defying something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    לים
    -0.08
    截至
    -0.07
    .binding
    -0.07
    قص
    -0.07
    把握
    -0.07
    ,private
    -0.07
    اوية
    -0.07
    黎
    -0.07
     gather
    -0.07
    穴
    -0.07
    POSITIVE LOGITS
    fab
    0.08
    変わ
    0.07
    昝
    0.07
    .CustomButton
    0.07
     decades
    0.06
     )[
    0.06
    轳
    0.06
    ᴡ
    0.06
    航班
    0.06
    _t
    0.06
    Act Density 0.007%

    No Known Activations