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

    Neuronpedia

    INDEX
    Explanations

    numerical values and specific identifiers

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

    numbered lists and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.49
    atguigu
    -0.47
     materialen
    -0.43
    classnames
    -0.42
     SafeMath
    -0.41
     gebruikers
    -0.41
     spesa
    -0.41
     voordelen
    -0.40
     eenvou
    -0.40
     tričko
    -0.40
    POSITIVE LOGITS
    AsUp
    0.52
     defaultstate
    0.49
    expandindo
    0.47
     quinto
    0.46
     Extragalactic
    0.46
     sexto
    0.46
    ToBounds
    0.44
    MarshalTo
    0.43
     fifth
    0.42
     cinquième
    0.42
    Act Density 0.361%

    No Known Activations