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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    otics
    -0.08
    ooks
    -0.07
    ojis
    -0.07
    patch
    -0.07
    .assets
    -0.07
    /linux
    -0.06
     salute
    -0.06
    اوي
    -0.06
    气
    -0.06
    ilih
    -0.06
    POSITIVE LOGITS
     greed
    0.06
    exampleInput
    0.06
     totaled
    0.06
    IZ
    0.05
    旅行
    0.05
    	glut
    0.05
     киш
    0.05
    AL
    0.05
     ı
    0.05
     vant
    0.05
    Act Density 0.019%

    No Known Activations