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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Олександ
    -0.07
     مباش
    -0.06
     başında
    -0.06
     〈
    -0.06
    　ﾞ
    -0.06
    ofire
    -0.06
     düny
    -0.06
    .”↵↵
    -0.06
    	Test
    -0.06
     Contractors
    -0.06
    POSITIVE LOGITS
     Outdoor
    0.07
    .Security
    0.07
     Ensemble
    0.07
     Claw
    0.07
     Income
    0.06
     git
    0.06
     ANT
    0.06
     vap
    0.06
    別
    0.06
     IA
    0.06
    Act Density 0.002%

    No Known Activations