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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to protocols and networking

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

    Tokens after hexadecimal numbers

    np_acts-logits-general · gemini-2.0-flash

    names of places or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.81
    __;
    -0.79
     JpaRepository
    -0.77
    IUrlHelper
    -0.69
    الحياه
    -0.69
    UnusedPrivate
    -0.67
     laſſen
    -0.66
     ligiloj
    -0.65
     kaynağından
    -0.65
    Personendaten
    -0.64
    POSITIVE LOGITS
     Indah
    0.35
     flotante
    0.34
     nõ
    0.28
     accion
    0.28
    Veja
    0.28
     ſtand
    0.28
    øv
    0.27
     entera
    0.27
    Saiba
    0.27
     león
    0.27
    Act Density 0.119%

    No Known Activations