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

    Neuronpedia

    INDEX
    Explanations

    video

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     호
    -0.06
    (rank
    -0.06
    태
    -0.06
     biết
    -0.06
    lbs
    -0.06
    /hooks
    -0.06
     Lyft
    -0.05
     ماده
    -0.05
     مواد
    -0.05
     ทอง
    -0.05
    POSITIVE LOGITS
     sep
    0.07
    рование
    0.07
    +C
    0.07
    (space
    0.07
     nanny
    0.07
     IF
    0.07
     Köy
    0.07
     单
    0.07
    receiver
    0.06
     incentive
    0.06
    Act Density 0.007%

    No Known Activations