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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    槭
    -0.08
    友
    -0.07
     hết
    -0.07
    סופ
    -0.07
    seq
    -0.07
    _INSTANCE
    -0.06
    .ud
    -0.06
    家企业
    -0.06
     EVP
    -0.06
    cube
    -0.06
    POSITIVE LOGITS
     ambos
    0.08
    	angle
    0.07
    憋
    0.07
    莫名其妙
    0.07
    aked
    0.07
    рит
    0.07
    繼續
    0.06
     bar
    0.06
    뷔
    0.06
     abandoned
    0.06
    Act Density 0.014%

    No Known Activations