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

    Neuronpedia

    INDEX
    Explanations

    behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enk
    -0.08
    "),
    -0.07
     Coh
    -0.07
     LAW
    -0.07
     san
    -0.07
    .sum
    -0.07
     corrupt
    -0.07
    arefa
    -0.07
     Pascal
    -0.07
    ())
    -0.06
    POSITIVE LOGITS
    تغ
    0.06
    луата
    0.06
    （笑
    0.06
    Waiting
    0.06
    	mysqli
    0.06
     Relevant
    0.06
    .MESSAGE
    0.06
     ($_
    0.06
     loại
    0.06
    .HashMap
    0.05
    Act Density 0.003%

    No Known Activations