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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.10
     are
    -0.09
    ,
    -0.09
     (
    -0.08
     an
    -0.08
    (nn
    -0.08
     .
    -0.08
     a
    -0.07
     ваши
    -0.07
     submitting
    -0.07
    POSITIVE LOGITS
    -to
    0.14
     to
    0.13
    to
    0.13
    _to
    0.12
     gotta
    0.11
     To
    0.11
    —to
    0.11
    _TO
    0.11
     TO
    0.11
    To
    0.11
    Act Density 1.784%

    No Known Activations