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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    都
    -0.07
    show
    -0.07
     fim
    -0.07
    _snd
    -0.07
     donation
    -0.06
     kết
    -0.06
     Shaw
    -0.06
     NA
    -0.06
     Dao
    -0.06
    HX
    -0.06
    POSITIVE LOGITS
    (memory
    0.06
     вну
    0.06
    (wait
    0.06
     fraud
    0.06
     використання
    0.06
    ك
    0.06
     undesirable
    0.06
     之
    0.06
     algún
    0.06
     Lös
    0.06
    Act Density 0.117%

    No Known Activations