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

    Neuronpedia

    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PRE
    -0.07
    MouseEvent
    -0.06
    _RDONLY
    -0.06
    _DUMP
    -0.06
     __________________
    -0.06
     poměrně
    -0.06
     arrog
    -0.06
     respectable
    -0.06
    _SPECIAL
    -0.06
    _validate
    -0.06
    POSITIVE LOGITS
     hommes
    0.07
    ibar
    0.07
     tally
    0.07
     threesome
    0.07
    SV
    0.06
     истории
    0.06
     historians
    0.06
     [\
    0.06
    責
    0.06
     enfants
    0.06
    Act Density 0.007%

    No Known Activations