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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conditions
    -0.08
    ۵
    -0.06
    ζό
    -0.06
    甲
    -0.06
    _bad
    -0.06
    쪽
    -0.06
    \brief
    -0.06
     lợi
    -0.06
    ITIVE
    -0.06
     hran
    -0.06
    POSITIVE LOGITS
    [layer
    0.06
     Namespace
    0.06
     scripture
    0.06
     misguided
    0.06
    .range
    0.06
     Surre
    0.06
    (gp
    0.06
    .ns
    0.06
    (Stream
    0.06
    Equ
    0.06
    Act Density 0.025%

    No Known Activations