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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash

    HTML forms and elements related to user input.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Huffman
    -0.07
     Cody
    -0.07
     algorithm
    -0.07
     Williamson
    -0.07
     Dickinson
    -0.07
    Hmm
    -0.06
     FileManager
    -0.06
    wm
    -0.06
    .Dimension
    -0.06
    Question
    -0.06
    POSITIVE LOGITS
     até
    0.09
    DES
    0.08
    ():
↵
    0.08
    ()?;↵
    0.08
    ]:
↵
    0.07
    探
    0.07
    ="">
↵
    0.07
    ":↵↵
    0.07
    ="">↵
    0.07
    烈
    0.07
    Act Density 0.006%

    No Known Activations