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

    Neuronpedia

    INDEX
    Explanations

    numerical values and statistics

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

    Numbers within a specific range (0-60)

    np_acts-logits-general · gemini-2.0-flash

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    scriptcase
    -0.58
    Geplaatst
    -0.57
     saites
    -0.57
    ↵↵↵
    -0.56
    Personensuche
    -0.54
    angliski
    -0.53
     Farina
    -0.52
    Демографія
    -0.51
     Deutschlands
    -0.51
     Erste
    -0.51
    POSITIVE LOGITS
     '{@
    0.65
     ½
    0.65
     Audiodateien
    0.64
    ½
    0.61
     Karab
    0.60
     مرئيه
    0.60
    GeneratedMessage
    0.58
    ofern
    0.56
    >{@
    0.56
    âmara
    0.55
    Act Density 0.378%

    No Known Activations