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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GRA
    -0.07
    etiyle
    -0.07
     erg
    -0.06
    $c
    -0.06
    比赛
    -0.06
     muit
    -0.06
    	command
    -0.06
    sut
    -0.06
     Тер
    -0.06
     decline
    -0.06
    POSITIVE LOGITS
    eur
    0.07
    off
    0.07
     Off
    0.07
    NING
    0.06
     on
    0.06
     On
    0.06
    λον
    0.06
     ON
    0.06
    _on
    0.06
     olds
    0.06
    Act Density 0.002%

    No Known Activations