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

    Neuronpedia

    INDEX
    Explanations

    Trying not to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     complement
    -0.08
     stamped
    -0.08
    raat
    -0.08
    рых
    -0.07
    ovement
    -0.07
     regard
    -0.07
     annih
    -0.07
     بسته
    -0.07
     بالط
    -0.07
    werkingen
    -0.07
    POSITIVE LOGITS
     upbeat
    0.09
     halluc
    0.09
     laughs
    0.08
     smiles
    0.08
     cheerful
    0.08
     sput
    0.08
     lol
    0.08
     readability
    0.08
     playful
    0.08
     вит
    0.08
    Act Density 0.019%

    No Known Activations