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

    Neuronpedia

    INDEX
    Explanations

    File headers and magic numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    četně
    -0.09
    त्या
    -0.08
    เรื่อง
    -0.08
     Shade
    -0.08
     yari
    -0.08
    lamak
    -0.08
     tolik
    -0.08
    lanan
    -0.08
     gyn
    -0.08
     shade
    -0.08
    POSITIVE LOGITS
     bytes
    0.10
    _bytes
    0.10
    Bytes
    0.09
     fingerprints
    0.09
     verifying
    0.09
    匹
    0.09
     confirming
    0.08
     совп
    0.08
     unmistak
    0.08
     recognizable
    0.08
    Act Density 0.004%

    No Known Activations