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

    Neuronpedia

    INDEX
    Explanations

    concepts related to definitions and theoretical constructs

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

    concept of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    消化
    -0.37
    Попис
    -0.37
     Signalez
    -0.36
    cesis
    -0.32
    บ้าง
    -0.32
     Lav
    -0.32
     morrow
    -0.31
    getragen
    -0.31
    anskje
    -0.30
    
    -0.30
    POSITIVE LOGITS
     concept
    1.20
    concept
    1.07
     concepto
    1.04
     conceito
    1.04
    Concept
    1.04
     Concept
    1.03
    概念
    0.98
     concepts
    0.97
     Concepts
    0.90
     CONCEPT
    0.88
    Act Density 0.022%

    No Known Activations