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

    Neuronpedia

    INDEX
    Explanations

    plateau

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gold
    -0.08
     jam
    -0.08
     unconditional
    -0.08
     disclosures
    -0.07
     सहभागी
    -0.07
     सहभाग
    -0.07
    .eth
    -0.07
     shipping
    -0.07
     sunglasses
    -0.07
    BS
    -0.07
    POSITIVE LOGITS
    形成
    0.09
    formatie
    0.09
     সৃষ্টি
    0.09
     tuss
    0.09
    cence
    0.09
    ([(
    0.09
    formations
    0.09
    velop
    0.08
     formed
    0.08
     formations
    0.08
    Act Density 0.015%

    No Known Activations