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

    Neuronpedia

    INDEX
    Explanations

    text related to gaming or Marvel entertainment franchises

    oai_token-act-pair · gemini-2.0-flash

    gaming, coding, fandom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.60
     y
    -0.57
     kasarigan
    -0.57
    #+#
    -0.54
    iesis
    -0.50
     N
    -0.47
     format
    -0.46
    ufo
    -0.45
    toppers
    -0.44
    washingtonpost
    -0.43
    POSITIVE LOGITS
     itſelf
    0.69
    〢
    0.69
     Houſe
    0.66
     houſe
    0.66
    isContained
    0.66
     Diſ
    0.65
     Jefus
    0.64
    IVEREF
    0.63
    LEncoder
    0.63
     becauſe
    0.63
    Act Density 46.363%

    No Known Activations