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

    Neuronpedia

    INDEX
    Explanations

    topics related to news and current events

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

    Text appearing after certain symbols/words

    np_acts-logits-general · gemini-2.0-flash

    common words then specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     taban
    -0.42
     rígido
    -0.41
     sincerity
    -0.40
     strategi
    -0.40
    indrical
    -0.38
     modalités
    -0.37
    strategie
    -0.37
    ברית
    -0.37
    rahmen
    -0.36
     definitely
    -0.36
    POSITIVE LOGITS
     @"/
    0.81
    :✨
    0.78
    writeFieldEnd
    0.71
     lenker
    0.70
    今週
    0.70
    //
    0.70
    webElementXpaths
    0.69
    ethene
    0.69
    0.69
    اریخ
    0.69
    Act Density 0.139%

    No Known Activations