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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data or numerical information

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

    mathematical or programming contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jména
    -0.71
    WireFormatLite
    -0.58
    majánló
    -0.57
     '\\;'
    -0.52
    RegressionTest
    -0.52
     Wikiseite
    -0.50
    transQ
    -0.50
    WaitGroup
    -0.50
    devším
    -0.50
    setVerticalGroup
    -0.49
    POSITIVE LOGITS
     pen
    0.42
     pe
    0.41
     tat
    0.39
     sup
    0.38
     times
    0.36
    adpleegd
    0.35
     ste
    0.34
    ValueGeneration
    0.34
     len
    0.34
     mag
    0.34
    Act Density 0.002%

    No Known Activations