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

    Neuronpedia

    INDEX
    Explanations

    programming and mathematical expressions related to image processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical computation code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.42
     åt
    -0.39
     league
    -0.38
    出版年
    -0.36
    Spécification
    -0.35
    AsUp
    -0.35
    guenos
    -0.35
     sanitarias
    -0.34
     casque
    -0.34
     defaultstate
    -0.33
    POSITIVE LOGITS
     squeeze
    0.52
    reshape
    0.50
     reshape
    0.50
     diag
    0.48
     propOrder
    0.48
    帖最后由
    0.48
    WaitGroup
    0.47
     flip
    0.46
     transpose
    0.45
    double
    0.45
    Act Density 0.031%

    No Known Activations