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

    Neuronpedia

    INDEX
    Explanations

    quantitative mentions of attempts, studies, or observations in scientific contexts

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

    recent findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     muur
    -0.37
    ِّف
    -0.35
    espec
    -0.35
    alih
    -0.33
    当年
    -0.32
    ExecuteReader
    -0.32
    ->___
    -0.32
     Caul
    -0.31
     첫
    -0.31
     helft
    -0.31
    POSITIVE LOGITS
     recently
    1.35
    recently
    1.34
     recent
    1.34
    recent
    1.33
    Recently
    1.27
    Recent
    1.23
     Recently
    1.19
     recientemente
    1.17
     récemment
    1.16
     recentemente
    1.16
    Act Density 0.108%

    No Known Activations