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

    Neuronpedia

    INDEX
    Explanations

    terms related to roles or professions

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

    explaining likelihoods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XtraReports
    -0.52
    startActivity
    -0.46
    +#+#
    -0.46
    OGND
    -0.45
    >>()
    -0.44
    imédia
    -0.43
    blia
    -0.41
     تضيفلها
    -0.40
    原始内容存档于
    -0.40
    "}")
    -0.39
    POSITIVE LOGITS
     perhaps
    1.47
     indeed
    1.20
    perhaps
    1.19
     appunto
    1.13
     maybe
    1.10
     talvez
    1.09
    indeed
    1.08
     quizá
    1.07
     quizás
    1.03
     apparently
    1.02
    Act Density 0.189%

    No Known Activations