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

    Neuronpedia

    INDEX
    Explanations

    power on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UInteger
    0.38
    issati
    0.37
    usser
    0.36
    訾
    0.36
     бө
    0.35
    стьян
    0.35
    হর
    0.34
    rimiento
    0.34
     PLIST
    0.34
    ropoda
    0.33
    POSITIVE LOGITS
     On
    3.53
    On
    3.38
     ON
    3.13
     온
    2.86
    オン
    2.84
     ऑन
    2.83
    ON
    2.63
    온
    2.53
    ऑन
    2.38
    on
    2.33
    Act Density 0.136%

    No Known Activations