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

    Neuronpedia

    INDEX
    Explanations

    MIT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dividend
    -0.08
     LO
    -0.07
    '];?>
    -0.07
    .pro
    -0.07
     сос
    -0.06
    _half
    -0.06
     Benedict
    -0.06
     hosp
    -0.06
    infos
    -0.06
    且
    -0.06
    POSITIVE LOGITS
     وهو
    0.07
     offsetY
    0.06
    σιμοποι
    0.06
    toggle
    0.06
    场
    0.06
     anon
    0.06
    -bordered
    0.06
    owns
    0.06
    enance
    0.06
     схем
    0.06
    Act Density 0.002%

    No Known Activations