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

    Neuronpedia

    INDEX
    Explanations

    mathematical structures and relationships involving symbols and equations

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

    "Is" followed by definitions or equalities

    np_acts-logits-general · gemini-2.0-flash

    states definitions or equalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Winaray
    -0.54
    öbb
    -0.49
     WaitForSeconds
    -0.48
     تعدى
    -0.47
    toe
    -0.47
     Neu
    -0.45
    الحياه
    -0.44
    REME
    -0.44
    vode
    -0.44
    ː
    -0.44
    POSITIVE LOGITS
     defined
    0.87
     Defined
    0.78
    defined
    0.75
     calculated
    0.73
    دانشنامهٔ
    0.69
     défini
    0.68
     computed
    0.68
     égal
    0.67
    calculated
    0.67
     expressed
    0.63
    Act Density 1.344%

    No Known Activations