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

    Neuronpedia

    INDEX
    Explanations

    oss

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ǰ
    -0.08
    �
    -0.07
     juvenile
    -0.07
     handy
    -0.07
    	RTE
    -0.07
    瘭
    -0.07
    ourn
    -0.07
    önü
    -0.06
    棪
    -0.06
     decis
    -0.06
    POSITIVE LOGITS
    업체
    0.07
     OSP
    0.07
    卖家
    0.07
     ending
    0.06
    华侨
    0.06
    ᅟ
    0.06
     '':↵
    0.06
    审查
    0.06
     +↵
    0.06
    lex
    0.06
    Act Density 0.002%

    No Known Activations