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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to server configuration

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

    code block markers or diff lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsContent
    -0.43
    essages
    -0.43
    __]
    -0.42
    ospels
    -0.40
    ôtel
    -0.38
    archs
    -0.38
     Pich
    -0.38
    isional
    -0.37
     mitään
    -0.37
    ếc
    -0.37
    POSITIVE LOGITS
    GTCX
    0.59
    setVerticalGroup
    0.55
    IntoConstraints
    0.50
    Atsauces
    0.47
    makeConstraints
    0.43
    UnusedPrivate
    0.42
    BeginInit
    0.42
    /***/
    0.40
    verifyException
    0.40
    vábbi
    0.40
    Act Density 0.004%

    No Known Activations