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

    Neuronpedia

    INDEX
    Explanations

    recipients of services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parole
    -0.07
     izin
    -0.07
     YA
    -0.07
     selectors
    -0.07
    념
    -0.06
     communicates
    -0.06
    UDIO
    -0.06
     Porn
    -0.06
     tomatoes
    -0.06
     protesting
    -0.06
    POSITIVE LOGITS
    Is
    0.07
     ydk
    0.06
     stif
    0.06
     emot
    0.06
     subsidiary
    0.06
     그는
    0.06
    σιμοποι
    0.06
    Instead
    0.06
     JM
    0.06
     soils
    0.06
    Act Density 0.090%

    No Known Activations