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

    Neuronpedia

    INDEX
    Explanations

    set theory, cardinality

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    年に
    -0.07
     pregnancy
    -0.07
     thức
    -0.06
    munition
    -0.06
     negotiating
    -0.06
     episodes
    -0.06
     بیشتر
    -0.06
    Quick
    -0.06
     دلیل
    -0.06
    	Destroy
    -0.06
    POSITIVE LOGITS
     Perc
    0.07
    istle
    0.06
    。那
    0.06
     Eş
    0.06
    채
    0.06
    天堂
    0.06
     IPCC
    0.06
    锦
    0.06
     obten
    0.06
     rowData
    0.06
    Act Density 0.022%

    No Known Activations