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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åİļåİļ
    -0.30
    umo
    -0.28
    essenger
    -0.27
    âĢ¦)↵↵
    -0.27
    é¢Ī
    -0.26
    .Chain
    -0.25
    âĢ¦↵↵↵↵
    -0.25
    malink
    -0.25
     czÄĻsto
    -0.25
    iggs
    -0.25
    POSITIVE LOGITS
    matches
    0.25
     disgust
    0.25
    .unpack
    0.24
    -outs
    0.24
    unpack
    0.24
     match
    0.23
    XP
    0.23
    ç«Ļéķ¿
    0.23
     Execute
    0.23
    æ¯ĶæĪij
    0.23
    Act Density 0.003%

    No Known Activations