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

    Neuronpedia

    INDEX
    Explanations

    occurrences and patterns related to fractions and proportions

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

    quantities as fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.57
     GenerationType
    -0.57
    homonymie
    -0.54
    \{\\
    -0.51
     MotionEvent
    -0.45
    -0.43
     Buchen
    -0.43
     setLoading
    -0.43
     schuhe
    -0.43
     denuncias
    -0.43
    POSITIVE LOGITS
    thirds
    0.77
     thirds
    0.65
    ⅔
    0.62
     Drittel
    0.62
    ⅓
    0.60
    ⅘
    0.59
     betweenstory
    0.59
     metade
    0.55
     Hälfte
    0.54
     half
    0.53
    Act Density 0.011%

    No Known Activations