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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to scientific methods and processes

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

    Tokens preceding parentheses, brackets, or quotes

    np_acts-logits-general · gemini-2.0-flash

    describes sequence above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.77
     estimés
    -0.69
    DIPSETTING
    -0.68
    ArgsConstructor
    -0.67
    TagMode
    -0.65
    #
    -0.64
    thâu
    -0.63
     jsPsych
    -0.60
    twimg
    -0.60
     فريبيس
    -0.59
    POSITIVE LOGITS
     here
    0.80
     mentioning
    0.79
     mention
    0.78
     aquí
    0.76
     paragraph
    0.71
     DESCR
    0.70
     spoilers
    0.70
    在这里
    0.70
     paragraphs
    0.69
    here
    0.69
    Act Density 0.412%

    No Known Activations