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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related terms and names

    np_acts-logits-general · gemini-2.0-flash

    listing items individually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #+#
    -0.48
    -0.47
    ragalactic
    -0.45
    AnchorStyles
    -0.45
    manjaro
    -0.45
    Rè
    -0.45
    AISSEE
    -0.44
     незавершена
    -0.44
    ніципалі
    -0.44
    GEBURTSDATUM
    -0.43
    POSITIVE LOGITS
    一个个
    0.63
     allemaal
    0.53
     birbir
    0.51
     collectively
    0.51
     successively
    0.50
     individually
    0.49
     each
    0.49
     instances
    0.48
     consecutively
    0.48
     sequentially
    0.46
    Act Density 1.805%

    No Known Activations