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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Ag
    -0.07
     гара
    -0.07
    ']?>"
    -0.07
    dna
    -0.07
     дека
    -0.07
     โดย
    -0.07
     sı
    -0.06
    thesize
    -0.06
    -yellow
    -0.06
    이라
    -0.06
    POSITIVE LOGITS
     Sleeping
    0.06
    (TAG
    0.06
     museum
    0.06
     Tento
    0.06
     situace
    0.06
     courage
    0.06
    とも
    0.06
     Beth
    0.06
    ethnic
    0.06
    ENCY
    0.06
    Act Density 0.003%

    No Known Activations