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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming and data structures

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

    correcte, normale, essential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.95
     snippetHide
    -0.85
    AddTagHelper
    -0.84
    __::
    -0.84
     مشين
    -0.84
     utafitiHapana
    -0.78
    ﹧
    -0.78
    <unused41>
    -0.77
    <pad>
    -0.76
    [@BOS@]
    -0.76
    POSITIVE LOGITS
    ๆ
    0.44
     which
    0.39
     ๆ
    0.37
     للغاية
    0.37
    which
    0.36
     ביותר
    0.36
    ៗ
    0.35
     of
    0.34
     consisting
    0.32
     جدا
    0.29
    Act Density 0.013%

    No Known Activations