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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,e
    -0.07
     trop
    -0.06
     chịu
    -0.06
    (Dialog
    -0.06
     Courier
    -0.06
    ()['
    -0.06
     حذف
    -0.06
    [m
    -0.06
     weekend
    -0.06
     推
    -0.06
    POSITIVE LOGITS
     Beverly
    0.11
    ayan
    0.08
    --}}↵
    0.07
    宿
    0.07
    รณ
    0.06
     cloves
    0.06
    rian
    0.06
     bravery
    0.06
     ι
    0.06
     Vibr
    0.06
    Act Density 0.014%

    No Known Activations