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

    Neuronpedia

    INDEX
    Explanations

    specific programming or code-related terms and structures

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

    utility keywords or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.54
    extAlignment
    -0.36
    plish
    -0.33
     variantes
    -0.32
    setopt
    -0.30
    นั้น
    -0.29
    ๆ
    -0.29
     inspiring
    -0.29
     bes
    -0.29
    inspiring
    -0.29
    POSITIVE LOGITS
     withRouter
    2.20
     pleaſure
    0.63
     houſe
    0.63
     ſch
    0.61
     myſelf
    0.60
    bootstrapcdn
    0.59
     faſt
    0.58
     Reſ
    0.57
     Monfieur
    0.57
     fubject
    0.57
    Act Density 0.001%

    No Known Activations