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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values or symbols, such as phone numbers or mathematical expressions

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

    Phone numbers and email addresses

    np_acts-logits-general · gemini-2.0-flash

    phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UNRELATED
    -0.56
    пет
    -0.45
     forKey
    -0.43
    CDCl
    -0.43
    énario
    -0.43
     dezen
    -0.42
     onPostExecute
    -0.42
    estr
    -0.42
     onPause
    -0.42
     freg
    -0.42
    POSITIVE LOGITS
     Samaria
    0.72
     aught
    0.70
    OGND
    0.69
     disambiguazione
    0.69
    KommentareTeilen
    0.66
     Morav
    0.65
     cromado
    0.65
    )$_
    0.64
     Meksiku
    0.64
    UrlResolution
    0.63
    Act Density 0.080%

    No Known Activations