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

    Neuronpedia

    INDEX
    Explanations

    train

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _REFERENCE
    -0.07
    uss
    -0.07
     *@
    -0.07
    DNS
    -0.06
     методи
    -0.06
     zvíř
    -0.06
    .Promise
    -0.06
    .Rad
    -0.06
     TED
    -0.06
    rement
    -0.06
    POSITIVE LOGITS
    ################################################################################
    0.07
     grass
    0.06
     AppleWebKit
    0.06
    voje
    0.06
    _main
    0.06
     paranormal
    0.06
    direction
    0.06
     rects
    0.06
     tableLayoutPanel
    0.06
    관리
    0.06
    Act Density 0.017%

    No Known Activations