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

    Neuronpedia

    INDEX
    Explanations

    specific mathematical or programming expressions and structures

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

    mathematical expressions in a specific form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.63
    expandindo
    -0.62
     jScrollPane
    -0.60
     UIAlert
    -0.56
     whiteColor
    -0.50
     cdr
    -0.50
    liceerd
    -0.49
     AppCompatTheme
    -0.48
    Portail
    -0.48
     ویکی‌پدیا
    -0.47
    POSITIVE LOGITS
     surla
    0.51
    fjspx
    0.46
     <<<<<<<<<<<<<<
    0.44
     Grüsse
    0.42
    ✨:
    0.40
    biega
    0.39
    ])+
    0.38
     yks
    0.38
    brać
    0.38
     černé
    0.38
    Act Density 0.342%

    No Known Activations