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

    Neuronpedia

    INDEX
    Explanations

    virus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的时候
    -0.07
    这样
    -0.07
     allocation
    -0.06
    орон
    -0.06
    REET
    -0.06
     hawk
    -0.06
     торгов
    -0.06
     گو
    -0.06
     투
    -0.06
     تح
    -0.06
    POSITIVE LOGITS
     فرمان
    0.07
    -split
    0.07
     obec
    0.06
    bral
    0.06
    iterals
    0.06
     hizmeti
    0.06
    avir
    0.06
    Assertions
    0.06
    Ngh
    0.06
     */;↵
    0.06
    Act Density 0.014%

    No Known Activations