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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and list structures

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

    Code or math delimiters

    np_acts-logits-general · gemini-2.0-flash

    code symbols followed by i

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ii
    -0.57
     iii
    -0.50
    APIC
    -0.49
     Winaray
    -0.47
    ssis
    -0.46
    
    -0.46
    antum
    -0.45
    KOK
    -0.45
    Aziz
    -0.44
    ulk
    -0.44
    POSITIVE LOGITS
     I
    1.25
    I
    1.21
    i
    0.82
    ฉัน
    0.77
     ویکی‌پدیا
    0.72
     я
    0.69
    我说
    0.69
    ผม
    0.69
    oneofs
    0.68
    我还
    0.68
    Act Density 0.204%

    No Known Activations