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

    Neuronpedia

    INDEX
    Explanations

    prepositions and adverbs indicating direction or location

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

    spatial prepositions and adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.88
     يتيمه
    -0.64
    󠁣
    -0.59
     فريبيس
    -0.56
    fromnode
    -0.56
    yntaxException
    -0.52
    XmlAccessType
    -0.50
    +#+#
    -0.50
    AsUp
    -0.49
    Према
    -0.49
    POSITIVE LOGITS
     chase
    0.44
    MathML
    0.43
    junit
    0.41
    RuleContext
    0.41
     store
    0.40
     Reynolds
    0.40
     Hunt
    0.39
     Baldwin
    0.39
     Parry
    0.39
     قلم
    0.38
    Act Density 0.076%

    No Known Activations