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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations related to sets and operations

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

    punctured neighbourhood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     StatelessWidget
    -0.59
     Administrativna
    -0.56
    mergeFrom
    -0.54
     disambiguazione
    -0.50
    AndEndTag
    -0.50
    Diweddarwch
    -0.48
    \{\\
    -0.48
     consultato
    -0.44
    Personendaten
    -0.43
     nakalista
    -0.41
    POSITIVE LOGITS
     Vors
    0.45
    ISupport
    0.43
    enderror
    0.41
     excluding
    0.39
    orté
    0.38
    ない
    0.37
    pola
    0.37
     الرياضيه
    0.36
    Vors
    0.36
     Lä
    0.36
    Act Density 0.106%

    No Known Activations