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

    Neuronpedia

    INDEX
    Explanations

    references to statistics and numerical data related to health

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

    Prepositions and articles

    np_acts-logits-general · gemini-2.0-flash

    phrase or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Utilize
    -0.57
     fresh
    -0.55
    gatsby
    -0.55
    梗
    -0.55
     indeed
    -0.54
     muscles
    -0.53
     utilizes
    -0.53
     Around
    -0.52
     bad
    -0.52
     history
    -0.52
    POSITIVE LOGITS
    WebElementEntity
    0.73
     propOrder
    0.65
     виправивши
    0.63
    rrggbb
    0.63
    }.
    0.63
     dAtA
    0.62
    '>
    0.61
     ferons
    0.60
    ’.”
    0.59
    ']}
    0.59
    Act Density 0.060%

    No Known Activations