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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DOCKER
    -0.07
    grad
    -0.07
     Weaver
    -0.07
    Protocol
    -0.07
     legislation
    -0.07
     wheelchair
    -0.07
     counselor
    -0.07
     typ
    -0.06
    -Day
    -0.06
    odní
    -0.06
    POSITIVE LOGITS
    indexOf
    0.06
    IColor
    0.06
    kanı
    0.06
     Học
    0.06
    ーブ
    0.06
     змі
    0.06
     ремонт
    0.06
    вер
    0.06
     Hue
    0.06
    Chris
    0.05
    Act Density 0.057%

    No Known Activations