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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =self
    -0.07
     composer
    -0.06
    ικός
    -0.06
    itzerland
    -0.06
    金属
    -0.06
    <Form
    -0.06
    _hero
    -0.06
     배열
    -0.06
     contrat
    -0.06
     Firestore
    -0.06
    POSITIVE LOGITS
    _extract
    0.07
     recalled
    0.07
    ential
    0.06
    ыс
    0.06
    URATION
    0.06
     ※
    0.06
     详情
    0.06
    urar
    0.06
     gly
    0.06
    rif
    0.06
    Act Density 0.007%

    No Known Activations