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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cps
    -0.06
     GENERIC
    -0.06
    stitute
    -0.06
     드립니다
    -0.06
     limit
    -0.06
     önce
    -0.06
    ладу
    -0.06
     UITextView
    -0.06
    -nav
    -0.06
    Stars
    -0.06
    POSITIVE LOGITS
     UIScreen
    0.07
     donner
    0.07
    ця
    0.07
    alloca
    0.07
    lem
    0.06
     energia
    0.06
    urma
    0.06
     Sho
    0.06
    Bern
    0.06
     у
    0.06
    Act Density 0.125%

    No Known Activations