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

    Neuronpedia

    INDEX
    Explanations

    details related to service quality in various contexts

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

    followed by commas or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    types of nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]--;
    -0.64
     /*#__
    -0.58
    =?";
    -0.57
    pps
    -0.56
     differently
    -0.55
     differs
    -0.55
     فقال
    -0.54
    artige
    -0.54
    warzys
    -0.54
     chronologically
    -0.53
    POSITIVE LOGITS
     الحره
    0.82
     coupled
    0.63
     compared
    0.60
     mean
    0.59
    mean
    0.58
     combined
    0.57
     AssemblyCompany
    0.57
     throughout
    0.57
    ExtendWith
    0.55
     mergeFrom
    0.55
    Act Density 0.706%

    No Known Activations