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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that signal a conclusion or finality

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

    words after start of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.66
    хьтан
    -0.57
     مشين
    -0.56
     otomatig
    -0.54
    OGND
    -0.53
    skjaer
    -0.49
    webElementXpaths
    -0.48
    arakat
    -0.48
    awtextra
    -0.48
    IActionResult
    -0.48
    POSITIVE LOGITS
    原始内容存档于
    0.38
    httphttps
    0.36
     palmas
    0.35
     spills
    0.35
     Palest
    0.34
     Already
    0.34
     encontrarse
    0.34
    倒
    0.34
    ПС
    0.33
     constitu
    0.33
    Act Density 0.002%

    No Known Activations