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

    Neuronpedia

    INDEX
    Explanations

    complex numerical data and percentages related to measurements or scores

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

    typical quantitative descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UIControlState
    -0.48
     Exe
    -0.47
    saraba
    -0.46
     localObject
    -0.44
    :✨
    -0.43
    multer
    -0.43
     multer
    -0.42
    ंदीखरीदारी
    -0.42
     intere
    -0.42
     gar
    -0.42
    POSITIVE LOGITS
     généralement
    0.65
     generalmente
    0.61
     typically
    0.58
     geralmente
    0.56
     gewöhnlich
    0.55
     suelen
    0.55
     najczęściej
    0.55
    typically
    0.54
     civilización
    0.53
     souvent
    0.52
    Act Density 0.092%

    No Known Activations