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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    folk
    -0.07
     cope
    -0.07
     wreckage
    -0.07
     sak
    -0.07
    Maps
    -0.07
     Leakage
    -0.07
     arrow
    -0.07
     wreck
    -0.07
    _GAIN
    -0.06
    亡
    -0.06
    POSITIVE LOGITS
    驗
    0.06
    リス
    0.06
     ceremon
    0.06
    .AUTH
    0.06
     satış
    0.06
    	async
    0.06
     defStyle
    0.06
    967
    0.06
     Th
    0.06
    .twig
    0.06
    Act Density 0.000%

    No Known Activations