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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and structure in various coding languages

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

    maximum values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.49
     للمعارف
    -0.44
     livrer
    -0.40
    তথ্যসূত্র
    -0.34
    ritten
    -0.33
     đủ
    -0.33
     cometh
    -0.32
    次
    -0.32
     Stimme
    -0.32
    นวน
    -0.31
    POSITIVE LOGITS
     max
    1.15
     getMax
    1.09
     Maximum
    1.09
     maximum
    1.08
    Max
    1.05
    max
    1.05
    Maximum
    1.05
     Max
    1.02
    maximum
    1.01
    getMax
    0.98
    Act Density 0.069%

    No Known Activations