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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate quantity or proportion

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

    Prepositions followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    number of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.59
     Photocase
    -0.56
     Infórmanos
    -0.54
    KommentareTeilen
    -0.53
    Сылтамалар
    -0.51
    CROSSTALK
    -0.49
     createSprite
    -0.49
    ことはありません
    -0.48
     становника
    -0.48
    ImageContext
    -0.48
    POSITIVE LOGITS
     belleza
    0.41
     beauty
    0.40
     littérature
    0.40
     bluse
    0.40
    ification
    0.40
     partita
    0.39
    リエーション
    0.39
    Conversion
    0.39
    Market
    0.39
    Trends
    0.39
    Act Density 0.905%

    No Known Activations