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

    Neuronpedia

    INDEX
    Explanations

    key attributes and significant factors in various contexts, including dimensions, contributions, and responsibilities

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

    initial / first sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.66
     autorytatywna
    -0.53
    uxxxx
    -0.52
    RTEE
    -0.51
    QMetaType
    -0.49
    ddots
    -0.48
    клопе
    -0.48
     kaarangay
    -0.47
    addCriterion
    -0.47
    skyl
    -0.47
    POSITIVE LOGITS
     ✭✭
    0.44
     awal
    0.43
    Initial
    0.36
     initial
    0.36
    RTCF
    0.35
     первую
    0.35
     principales
    0.35
     dasar
    0.34
     jinak
    0.34
     core
    0.34
    Act Density 0.117%

    No Known Activations