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

    Neuronpedia

    INDEX
    Explanations

    references to modifiers in language, particularly adjectives and their functions

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

    adjectives, modifiers, and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.53
    PointerException
    -0.44
    JspWriter
    -0.44
     ProtoMessage
    -0.43
    principalColumn
    -0.42
    matchCondition
    -0.42
     للمعارف
    -0.41
    HasIndex
    -0.40
    abetes
    -0.39
    Personensuche
    -0.39
    POSITIVE LOGITS
     participle
    0.57
     attribute
    0.54
     adjective
    0.54
    adjective
    0.53
    attribute
    0.50
    describing
    0.49
     describe
    0.49
     autorytatywna
    0.48
     adjectives
    0.48
     Attribute
    0.47
    Act Density 0.031%

    No Known Activations