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

    Neuronpedia

    INDEX
    Explanations

    null

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lég
    -0.07
    ｵ
    -0.07
    Ⰲ
    -0.07
     soph
    -0.07
     Respons
    -0.06
    XmlAttribute
    -0.06
    סט
    -0.06
     Genç
    -0.06
    フェ
    -0.06
     colore
    -0.06
    POSITIVE LOGITS
     Marian
    0.07
    (handle
    0.07
    uate
    0.07
    ϑ
    0.07
     Pulse
    0.07
    强化
    0.07
    }));↵
    0.07
     uplift
    0.07
    unda
    0.07
     כול
    0.07
    Act Density 0.002%

    No Known Activations