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
    ilities
    -0.07
    	f
    -0.07
     //</
    -0.06
     hospitalized
    -0.06
    拜
    -0.06
    hon
    -0.06
     avid
    -0.06
     Blackhawks
    -0.06
    .AreEqual
    -0.06
     servlet
    -0.06
    POSITIVE LOGITS
     componentWill
    0.06
     영향
    0.06
     اصول
    0.06
     solution
    0.06
     운영자
    0.06
    (layers
    0.06
     nombreux
    0.06
     fools
    0.06
    consume
    0.06
    adoo
    0.06
    Act Density 0.000%

    No Known Activations