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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tir
    -0.09
    ejs
    -0.07
     ”
    -0.07
     Mixer
    -0.07
     pov
    -0.07
     sund
    -0.06
     steals
    -0.06
    =search
    -0.06
     Lester
    -0.06
     مثل
    -0.06
    POSITIVE LOGITS
    erview
    0.06
     Fle
    0.06
     acceleration
    0.06
    _contrib
    0.06
    -resolution
    0.06
    oneksi
    0.06
    ้งาน
    0.06
    撮
    0.06
    _SM
    0.06
     TITLE
    0.06
    Act Density 0.063%

    No Known Activations