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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Jean
    -0.07
    adoras
    -0.06
    ourt
    -0.06
    moves
    -0.06
    (src
    -0.06
     生
    -0.06
    Hub
    -0.06
    Fran
    -0.06
    02
    -0.06
    Č
    -0.06
    POSITIVE LOGITS
    小说
    0.06
     cpt
    0.06
     MCU
    0.06
     uniformly
    0.06
    aec
    0.06
     Animated
    0.06
    eyle
    0.06
    ρι
    0.06
    PER
    0.06
     ση
    0.06
    Act Density 0.064%

    No Known Activations