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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FIR
    -0.06
     Prices
    -0.06
     lis
    -0.06
    beb
    -0.06
    HOOK
    -0.06
    getList
    -0.06
    	sys
    -0.06
    чен
    -0.06
     AJ
    -0.05
    ｢
    -0.05
    POSITIVE LOGITS
     roofing
    0.07
     남자
    0.07
    444
    0.07
    09
    0.06
     creditor
    0.06
    196
    0.06
     لباس
    0.06
    -destruct
    0.06
    -template
    0.06
     trí
    0.06
    Act Density 0.002%

    No Known Activations