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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating thoroughness or all-encompassing descriptions

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

    comprehensive reports and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Máy
    -0.43
    Machine
    -0.39
     değ
    -0.39
    araoh
    -0.38
    sleep
    -0.38
    paravant
    -0.38
    Хьажоргаш
    -0.38
     Robots
    -0.38
     roost
    -0.37
    shirt
    -0.37
    POSITIVE LOGITS
     comprehensive
    2.17
    comprehensive
    1.98
     Comprehensive
    1.88
    Comprehensive
    1.86
     comprehensively
    1.53
    prehensive
    1.24
     comprehen
    1.13
     umfass
    1.13
     extensive
    1.04
    综合
    1.00
    Act Density 0.003%

    No Known Activations