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

    Neuronpedia

    INDEX
    Explanations

    build failures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    年代
    -0.07
     samot
    -0.06
    _group
    -0.06
    Rick
    -0.06
    TXT
    -0.06
     требования
    -0.06
    asher
    -0.06
    rites
    -0.05
     sexes
    -0.05
     figsize
    -0.05
    POSITIVE LOGITS
    tiny
    0.08
     choke
    0.07
    Không
    0.07
    ỳ
    0.07
    ioxide
    0.06
     लक
    0.06
     slump
    0.06
    ürn
    0.06
     nhiễm
    0.06
    (Sql
    0.06
    Act Density 0.051%

    No Known Activations