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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    险
    -0.07
     replicate
    -0.07
    �
    -0.07
     рож
    -0.07
     TAS
    -0.06
     yazı
    -0.06
     Hab
    -0.06
    סביר
    -0.06
    anse
    -0.06
    оде
    -0.06
    POSITIVE LOGITS
     gladly
    0.07
     SINGLE
    0.07
    尤其是在
    0.07
    重要原因
    0.07
     "->
    0.07
     thanked
    0.07
     infile
    0.07
    ѷ
    0.07
    toPromise
    0.06
     beste
    0.06
    Act Density 0.000%

    No Known Activations