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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and calculations involving variables and expressions

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

    mathematical and code expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consenso
    -0.35
    sodik
    -0.34
     caisse
    -0.33
     estat
    -0.32
     reto
    -0.31
     reconoci
    -0.31
    ￣)
    -0.31
    ktı
    -0.31
    Diweddarwch
    -0.31
     silicona
    -0.30
    POSITIVE LOGITS
    ########.
    0.62
    mtrl
    0.60
    Autoritní
    0.57
     pinulongan
    0.57
    Hochspringen
    0.55
    ActionCreators
    0.54
     الرياضيه
    0.54
    AndEndTag
    0.53
     nahilalakip
    0.52
     StatefulWidget
    0.51
    Act Density 0.001%

    No Known Activations