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

    Neuronpedia

    INDEX
    Explanations

    cod

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ner
    -0.07
     ansch
    -0.07
     Burger
    -0.07
    .serializer
    -0.07
     perse
    -0.06
    筜
    -0.06
     textStatus
    -0.06
     Cons
    -0.06
    쟝
    -0.06
    火锅
    -0.06
    POSITIVE LOGITS
    onesia
    0.09
     glaring
    0.08
    イラ
    0.07
    햠
    0.07
    phi
    0.07
     refugees
    0.07
     ripping
    0.07
    IVATE
    0.07
    ~~~~
    0.07
     Figure
    0.06
    Act Density 0.003%

    No Known Activations