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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.10
     and
    -0.09
     ראש
    -0.08
     by
    -0.07
     Jacob
    -0.07
     chir
    -0.07
     (
    -0.07
     Car
    -0.07
     Gaz
    -0.06
    -0.06
    POSITIVE LOGITS
    所提供
    0.08
     exped
    0.08
    _su
    0.07
     FileSystem
    0.07
    dıkt
    0.07
     \
    0.07
    uckets
    0.07
    apsed
    0.06
    .flatMap
    0.06
    	parser
    0.06
    Act Density 0.097%

    No Known Activations