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

    Neuronpedia

    INDEX
    Explanations

    references to scientific and technical details in various contexts

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

    Characters immediately preceding a number

    np_acts-logits-general · gemini-2.0-flash

    foreign language or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DrawerToggle
    -0.48
    SequentialGroup
    -0.47
     OMITBAD
    -0.46
    AISSEE
    -0.46
     queſta
    -0.45
     Италијани
    -0.45
     Administrativna
    -0.44
    awtextra
    -0.44
    NamedQueries
    -0.43
     amarillas
    -0.43
    POSITIVE LOGITS
     Chwiliwch
    0.46
     further
    0.44
    点此举报
    0.43
    NameInMap
    0.41
     additional
    0.41
    Tembelea
    0.40
     weitere
    0.40
    Derbyniad
    0.38
     للمعارف
    0.36
     Pur
    0.36
    Act Density 0.762%

    No Known Activations