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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section

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

    Tokens that precede numbers or fractions

    np_acts-logits-general · gemini-2.0-flash

    significant differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PhysRev
    -0.74
    setVerticalGroup
    -0.71
     purpoſe
    -0.71
     Majefty
    -0.67
    ArrowToggle
    -0.64
     houſe
    -0.64
     leſs
    -0.63
    tilhe
    -0.63
     Houſe
    -0.63
     reaſon
    -0.63
    POSITIVE LOGITS
    AnimationsModule
    0.51
     First
    0.44
    ंदीखरीदारी
    0.43
     للاسماء
    0.41
    First
    0.41
     eerste
    0.41
    ="@+
    0.41
     popol
    0.40
    1
    0.40
    GEBURTSDATUM
    0.40
    Act Density 0.147%

    No Known Activations