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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .untracked
    -0.07
    _equ
    -0.07
     disgu
    -0.06
     Hence
    -0.06
    ить
    -0.06
     eag
    -0.06
     diplomats
    -0.06
    iddy
    -0.06
    행
    -0.06
    іє
    -0.06
    POSITIVE LOGITS
    xffffff
    0.06
    _word
    0.06
     tainted
    0.06
     зак
    0.06
    職
    0.06
     白
    0.06
     han
    0.06
    (square
    0.06
     зах
    0.06
    .clearRect
    0.06
    Act Density 0.047%

    No Known Activations