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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    越
    -0.06
    ила
    -0.06
    imar
    -0.06
    loquent
    -0.06
     noc
    -0.06
    ΙΛ
    -0.06
     bilim
    -0.06
     yr
    -0.06
    [h
    -0.06
     rhyme
    -0.06
    POSITIVE LOGITS
    個
    0.07
    愛
    0.07
     MCP
    0.07
    승
    0.06
    _RESERVED
    0.06
    _Un
    0.06
    profit
    0.06
     краї
    0.06
    ＼＼
    0.06
     seks
    0.06
    Act Density 0.020%

    No Known Activations