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

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CELL
    -0.07
    kul
    -0.07
    constitution
    -0.07
    _FORM
    -0.06
    olics
    -0.06
     stout
    -0.06
    delay
    -0.06
     gums
    -0.06
    .ToLower
    -0.06
    लग
    -0.06
    POSITIVE LOGITS
     pau
    0.06
     ماد
    0.06
     Kirby
    0.06
     Heb
    0.06
     kỹ
    0.06
     Don
    0.06
     founders
    0.06
    指
    0.06
    "This
    0.06
     котором
    0.06
    Act Density 0.007%

    No Known Activations