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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantities and relationships within a group

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

    quantifiers introducing descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.45
    haikusbot
    -0.37
     dagegen
    -0.37
    omiast
    -0.36
    LikeLike
    -0.36
     bershka
    -0.35
     málaga
    -0.35
    metra
    -0.34
    marvin
    -0.34
     Timur
    -0.34
    POSITIVE LOGITS
     BoxDecoration
    0.65
     AssemblyCulture
    0.60
     يتيمه
    0.55
     Administrativna
    0.51
     nahilalakip
    0.51
    rungsseite
    0.50
    ✨:
    0.49
    adpleegd
    0.45
    ArgsConstructor
    0.44
    WireFormat
    0.44
    Act Density 0.040%

    No Known Activations