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

    Neuronpedia

    INDEX
    Explanations

    continuous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    url
    -0.07
    іка
    -0.07
     Router
    -0.06
     мар
    -0.06
     ま
    -0.06
     fel
    -0.06
     reson
    -0.06
    cient
    -0.06
    -most
    -0.06
     defiance
    -0.06
    POSITIVE LOGITS
    HELP
    0.06
    Backdrop
    0.06
    ريق
    0.06
    serir
    0.06
     marched
    0.06
     ""))↵
    0.06
     touches
    0.06
     вещ
    0.06
    (','
    0.06
    tain
    0.06
    Act Density 0.150%

    No Known Activations