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

    Neuronpedia

    INDEX
    Explanations

    entered

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _plugin
    -0.08
    InInspector
    -0.07
     punches
    -0.07
     exactly
    -0.07
    ünü
    -0.07
    prü
    -0.07
    *A
    -0.07
    lica
    -0.07
    	cout
    -0.07
    (operation
    -0.06
    POSITIVE LOGITS
    消毒
    0.07
     Goldberg
    0.07
    offsetof
    0.07
     Neville
    0.07
    運動
    0.06
     Meadows
    0.06
     whales
    0.06
    排行榜
    0.06
    -half
    0.06
    .maps
    0.06
    Act Density 0.000%

    No Known Activations