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

    Neuronpedia

    INDEX
    Explanations

    physical/mathematical structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utes
    -0.28
    èŀį
    -0.27
    ório
    -0.27
    *
    -0.26
    .just
    -0.26
    pees
    -0.25
    pee
    -0.25
     hands
    -0.25
    è·¨
    -0.24
    ubs
    -0.24
    POSITIVE LOGITS
    Scripts
    0.30
     COPYING
    0.26
     Colomb
    0.26
    æ¶ķ
    0.25
     inventions
    0.25
     Filip
    0.25
    _CALLBACK
    0.25
    åIJij举
    0.24
    رÙĬس
    0.24
    åįļ士
    0.24
    Act Density 0.284%

    No Known Activations