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

    Neuronpedia

    INDEX
    Explanations

    Array

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     본
    -0.06
    、三
    -0.06
     самост
    -0.06
     краї
    -0.06
     ninh
    -0.06
    ิโ
    -0.06
    вана
    -0.06
     Emil
    -0.06
    Death
    -0.06
     Colomb
    -0.06
    POSITIVE LOGITS
    itchens
    0.07
    _del
    0.07
     비교
    0.07
     accessing
    0.06
     Hoover
    0.06
    =settings
    0.06
     demographic
    0.06
    (EFFECT
    0.06
     naughty
    0.06
     Dex
    0.06
    Act Density 0.007%

    No Known Activations