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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unidad
    -0.07
    uddle
    -0.06
    ρθ
    -0.06
     &:
    -0.06
    -square
    -0.06
     avis
    -0.06
    sti
    -0.06
    uliar
    -0.06
    ellung
    -0.06
    icients
    -0.06
    POSITIVE LOGITS
    グ
    0.07
    arsing
    0.06
     мар
    0.06
     이
    0.06
    ecret
    0.06
    (Print
    0.06
    async
    0.06
    ось
    0.06
    	dir
    0.06
    0.05
    Act Density 0.006%

    No Known Activations