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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mir
    -0.07
     şeyler
    -0.07
    ились
    -0.07
     Maur
    -0.07
    ัน
    -0.06
     Phone
    -0.06
    gado
    -0.06
     Fle
    -0.06
    ůj
    -0.06
     MEMORY
    -0.06
    POSITIVE LOGITS
    >f
    0.06
    _ring
    0.06
    "}>↵
    0.06
     бесп
    0.06
    HasForeignKey
    0.06
    σιεύ
    0.06
    etSocketAddress
    0.06
    负
    0.06
    危
    0.06
    ƒ
    0.05
    Act Density 0.004%

    No Known Activations