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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chairs
    -0.07
    中秋
    -0.07
    '])->
    -0.07
    multiple
    -0.07
    وة
    -0.07
    put
    -0.06
    ♰
    -0.06
    	val
    -0.06
     Braz
    -0.06
    .strptime
    -0.06
    POSITIVE LOGITS
    _temperature
    0.07
     roaming
    0.07
     película
    0.07
     vistas
    0.07
     haber
    0.06
     sterile
    0.06
    但这
    0.06
    :T
    0.06
    ꪖ
    0.06
    占地
    0.06
    Act Density 0.053%

    No Known Activations