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

    Neuronpedia

    INDEX
    Explanations

    expressions of success and achievement

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

    proper nouns and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noDo
    -0.66
     itſelf
    -0.65
    +#+#
    -0.65
    WriteTagHelper
    -0.65
     beginnetje
    -0.64
     برانيه
    -0.62
     kasarigan
    -0.61
     Monfieur
    -0.61
    enumi
    -0.60
    LookAnd
    -0.59
    POSITIVE LOGITS
    LabelTagHelper
    0.34
    <eos>
    0.32
     department
    0.30
    __',
    0.29
     anti
    0.29
     goals
    0.29
     departmental
    0.28
     insight
    0.27
    \)
    0.27
     compromiso
    0.26
    Act Density 0.019%

    No Known Activations