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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inquiry or investigation

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

    topics of discussion and narration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.42
    ReusableCell
    -0.41
    ✨:
    -0.39
    principalColumn
    -0.39
     doğal
    -0.38
     vertrou
    -0.36
    tagPool
    -0.36
    AddTagHelper
    -0.36
    Highland
    -0.36
    ousands
    -0.35
    POSITIVE LOGITS
    について
    1.80
     について
    1.33
     대해
    1.30
    に関して
    1.12
    についての
    1.10
    についても
    1.08
    については
    0.98
     대한
    0.94
     hakkında
    0.89
    に関する
    0.87
    Act Density 0.002%

    No Known Activations