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

    Neuronpedia

    INDEX
    Explanations

    Acronyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    قدر
    -0.06
    SHA
    -0.06
     Dropbox
    -0.06
     Nero
    -0.06
    ์พ
    -0.06
     yerini
    -0.06
    (vals
    -0.06
    خر
    -0.06
     εκεί
    -0.06
     türlü
    -0.06
    POSITIVE LOGITS
    <Group
    0.08
    &view
    0.07
    leased
    0.07
    합
    0.06
     Calcul
    0.06
    "],"
    0.06
     receives
    0.06
    発売
    0.06
     admired
    0.06
     star
    0.06
    Act Density 0.165%

    No Known Activations