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

    Neuronpedia

    INDEX
    Explanations

    ->

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sourced
    -0.08
     JetBrains
    -0.07
     lingerie
    -0.07
    ooky
    -0.07
    ασίας
    -0.06
     perc
    -0.06
     incididunt
    -0.06
    ovány
    -0.06
    ')))↵
    -0.06
     consid
    -0.06
    POSITIVE LOGITS
    *self
    0.08
    _CELL
    0.07
    落ち
    0.06
     %{
    0.06
     pitches
    0.06
     Accountability
    0.06
    Guest
    0.06
    allax
    0.06
    _BAL
    0.06
     आग
    0.06
    Act Density 0.018%

    No Known Activations