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

    Neuronpedia

    INDEX
    Explanations

    elements related to objects and their placement or usage in various contexts

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

    preposition followed by period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.71
     kasarigan
    -0.66
    ⪜
    -0.59
     パンチラ
    -0.55
    PyExc
    -0.55
     queſta
    -0.54
    <unused41>
    -0.53
    [@BOS@]
    -0.53
     geweſen
    -0.53
    <unused40>
    -0.53
    POSITIVE LOGITS
     passed
    0.31
     handed
    0.30
    లాలు
    0.30
     للاسماء
    0.29
    原标题
    0.29
     tucked
    0.28
     bloquear
    0.27
     ואת
    0.27
    ものです
    0.27
     holder
    0.26
    Act Density 0.031%

    No Known Activations