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

    Neuronpedia

    INDEX
    Explanations

    causative or conditional conjunctions and adverbs

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

    conjunctions introducing reasons or consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bul
    -0.44
     الس
    -0.42
     Sho
    -0.42
     nakalista
    -0.42
    centerline
    -0.41
     Sver
    -0.41
    Bul
    -0.41
    ampire
    -0.41
     mets
    -0.41
     Nere
    -0.40
    POSITIVE LOGITS
    uxxxx
    0.72
    SourceChecksum
    0.64
    fjspx
    0.58
     חיצוניים
    0.57
    StructEnd
    0.57
    الحياه
    0.53
     soñar
    0.52
     nonatomic
    0.52
    uesia
    0.52
    protoimpl
    0.51
    Act Density 0.063%

    No Known Activations