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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and responses in discussions

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

    elements related to programming functions and web development

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

    everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nteral
    -0.61
    #+#
    -0.58
     оригіналу
    -0.57
     बजाय
    -0.57
    httphttps
    -0.56
    chium
    -0.56
    ãng
    -0.55
    sidemargin
    -0.53
     pinulongan
    -0.53
    ristor
    -0.52
    POSITIVE LOGITS
     everything
    2.55
    everything
    2.36
     Everything
    2.25
    Everything
    2.23
     tudo
    1.71
     alles
    1.70
     EVERYTHING
    1.59
     wszystko
    1.56
     totul
    1.54
     всичко
    1.47
    Act Density 0.259%

    No Known Activations