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

    Neuronpedia

    INDEX
    Explanations

    software problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resonate
    -0.07
    服
    -0.07
    udd
    -0.06
     gradu
    -0.06
    Monster
    -0.06
    -functions
    -0.06
     년도별
    -0.06
     Ring
    -0.06
     ############################################################################
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    того
    0.07
     rifles
    0.07
    eview
    0.07
    容
    0.07
    :function
    0.06
    ply
    0.06
     الآ
    0.06
     [\
    0.06
    (curl
    0.06
     благ
    0.06
    Act Density 0.039%

    No Known Activations