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

    Neuronpedia

    INDEX
    Explanations

    grammar and language syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hé
    -0.07
     Week
    -0.07
    _Act
    -0.06
     Prevent
    -0.06
     Day
    -0.06
    .focus
    -0.06
    Progress
    -0.06
    mits
    -0.06
    “He
    -0.06
     evac
    -0.06
    POSITIVE LOGITS
    lü
    0.06
     aer
    0.06
    oplast
    0.06
    οκ
    0.06
     seguridad
    0.06
     ủy
    0.06
    ayar
    0.06
     gratuita
    0.06
    GetObject
    0.06
     Ether
    0.06
    Act Density 0.038%

    No Known Activations