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

    Neuronpedia

    INDEX
    Explanations

    Fictional character references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —one
    -0.07
     говорить
    -0.07
    )->
    -0.07
    —"
    -0.07
    _stride
    -0.06
    _tokens
    -0.06
     वर
    -0.06
     gen
    -0.06
     Shaman
    -0.06
     Coupe
    -0.06
    POSITIVE LOGITS
     السكان
    0.07
     anonym
    0.06
    [i
    0.06
    ,,,,,,,,
    0.06
    ###############################################################################↵
    0.06
     relic
    0.06
    [SerializeField
    0.06
    ическое
    0.06
    *k
    0.06
    ैय
    0.06
    Act Density 0.042%

    No Known Activations