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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a classification or categorization with a focus on the number "two."

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

    two followed by types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vaikka
    -0.46
    Koordinaten
    -0.43
    homonymie
    -0.41
     disambiguazione
    -0.41
    ⁱ
    -0.39
     fürs
    -0.39
    ReadInt
    -0.36
    üyada
    -0.36
    허
    -0.36
    ambién
    -0.35
    POSITIVE LOGITS
    satunya
    0.72
     two
    0.67
    有两个
    0.60
     Administrativna
    0.59
    two
    0.57
     defaultstate
    0.54
    Two
    0.53
     TWO
    0.53
     snippetHide
    0.52
     Two
    0.52
    Act Density 0.031%

    No Known Activations