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

    Neuronpedia

    INDEX
    Explanations

    the start of a document or paragraph

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

    Follows punctuation or a specific word

    np_acts-logits-general · gemini-2.0-flash

    medical examination or recall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -1.24
    تقاوى
    -1.11
    DeleteBehavior
    -0.95
     propOrder
    -0.93
    脚注の使い方
    -0.92
     चीज़ों
    -0.91
    AsUp
    -0.90
    featureID
    -0.85
    Portale
    -0.84
     Italijani
    -0.84
    POSITIVE LOGITS
    éndole
    0.56
     
    0.51
    inkel
    0.46
     G
    0.45
     Pip
    0.43
    hypothesis
    0.40
     I
    0.40
    PRESSED
    0.39
     hjär
    0.39
     häl
    0.39
    Act Density 0.074%

    No Known Activations