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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тобто
    -0.07
     Documentation
    -0.07
     těž
    -0.07
    ASH
    -0.07
    اشین
    -0.07
    ідно
    -0.07
    daughter
    -0.07
     Damon
    -0.06
     nunca
    -0.06
    ㅎ
    -0.06
    POSITIVE LOGITS
    么
    0.06
    nels
    0.06
    juan
    0.06
    績
    0.06
    ionale
    0.06
    ومی
    0.06
    urst
    0.06
    xia
    0.06
    more
    0.06
     توص
    0.06
    Act Density 0.063%

    No Known Activations