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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or codes in a structured format

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

    Characters followed by special symbols

    np_acts-logits-general · gemini-2.0-flash

    coded strings and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    R
    -1.00
    T
    -0.95
    S
    -0.90
    E
    -0.89
    M
    -0.82
    D
    -0.81
    I
    -0.79
    P
    -0.78
    C
    -0.78
    F
    -0.76
    POSITIVE LOGITS
    Personendaten
    0.73
    ʖ
    0.57
     disambiguazione
    0.55
    ❸
    0.53
    ❹
    0.51
    jší
    0.50
    الإنجليزية
    0.50
    Identyfik
    0.50
    Bibliograf
    0.48
    #+#
    0.47
    Act Density 0.541%

    No Known Activations