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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical or computational expressions

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

    conversational prompts or equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTS
    -0.38
     bumping
    -0.34
     물
    -0.34
     تضيفلها
    -0.34
     them
    -0.34
     doubly
    -0.34
     memorable
    -0.33
    jetbrains
    -0.33
     appoint
    -0.33
     пункт
    -0.33
    POSITIVE LOGITS
     autorytatywna
    0.80
    Personendaten
    0.74
    :✨
    0.72
     للمعارف
    0.66
    webElementXpaths
    0.66
     يتيمه
    0.64
    ↹
    0.63
    RegressionTest
    0.63
     Chwiliwch
    0.62
    Autoritní
    0.59
    Act Density 0.000%

    No Known Activations