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

    Neuronpedia

    INDEX
    Explanations

    catch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kèm
    -0.08
    一只手
    -0.07
    像是
    -0.07
    TEL
    -0.07
    揄
    -0.07
     dawn
    -0.07
     Enter
    -0.06
    ي
    -0.06
    นะคะ
    -0.06
    aciones
    -0.06
    POSITIVE LOGITS
    砚
    0.07
    周恩来
    0.07
    网友评论
    0.07
     Omaha
    0.06
    borah
    0.06
     PB
    0.06
    ubuntu
    0.06
    choose
    0.06
     جامعة
    0.06
    =='
    0.06
    Act Density 0.005%

    No Known Activations