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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating studies or evidence demonstrating effects or outcomes

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

    "shown that"

    np_acts-logits-general · gemini-2.0-flash

    findings presented as proven

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spørs
    -0.47
    explanation
    -0.43
    ंदीखरीदारी
    -0.39
     незавершена
    -0.39
    Logo
    -0.39
    city
    -0.38
     propOrder
    -0.38
     EconPapers
    -0.38
    talking
    -0.38
    virtual
    -0.38
    POSITIVE LOGITS
     AssemblyCulture
    0.65
     terbukti
    0.54
     observed
    0.52
     empirically
    0.52
     proven
    0.52
     found
    0.48
     identified
    0.47
    CrossRef
    0.46
     detected
    0.46
    Proven
    0.46
    Act Density 0.871%

    No Known Activations