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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Je
    -0.07
    Reuters
    -0.07
    John
    -0.07
    moth
    -0.07
    乏力
    -0.07
     Rose
    -0.06
     المجلس
    -0.06
     =~
    -0.06
    —the
    -0.06
    redni
    -0.06
    POSITIVE LOGITS
     Dates
    0.09
    »↵↵
    0.08
     orbits
    0.07
     Mundo
    0.07
    𝓃
    0.07
     stringify
    0.07
    </
    0.07
    0.07
    '</
    0.07
    .AllowGet
    0.07
    Act Density 0.003%

    No Known Activations