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

    Neuronpedia

    INDEX
    Explanations

    Colon and parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Deck
    -0.07
     coef
    -0.07
     docking
    -0.06
     heed
    -0.06
     walks
    -0.06
    _binding
    -0.06
     './
    -0.06
     leverage
    -0.06
     mover
    -0.06
     pouring
    -0.06
    POSITIVE LOGITS
    َة
    0.06
    Shortcut
    0.06
    eresa
    0.06
     hầu
    0.06
    ตรวจ
    0.06
     이러
    0.06
    既
    0.06
    /exp
    0.06
     eles
    0.06
     oy
    0.06
    Act Density 0.001%

    No Known Activations