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

    Neuronpedia

    INDEX
    Explanations

    patterns involving numeric values and operations

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

    mathematical expressions with sqrt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.79
    -0.78
     Geiſt
    -0.76
     ویکی‌آمباردا
    -0.73
     Waſſer
    -0.71
    AISSEE
    -0.71
     Geſch
    -0.70
    Билгалдахарш
    -0.70
     dieſe
    -0.69
    AndEndTag
    -0.69
    POSITIVE LOGITS
     (
    0.37
    underbrace
    0.36
     con
    0.36
     string
    0.34
     pel
    0.34
     red
    0.33
     no
    0.33
     No
    0.33
     Bren
    0.33
     RE
    0.32
    Act Density 0.143%

    No Known Activations