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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific temperatures and measurements

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

    "At" followed by a variety of words

    np_acts-logits-general · gemini-2.0-flash

    at specific conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.65
    ⓧ
    -0.64
    ########.
    -0.64
     виправивши
    -0.58
     autorytatywna
    -0.56
    存于互联网档案馆
    -0.56
    مراجع
    -0.56
    AddTagHelper
    -0.55
     lenker
    -0.53
    Referanser
    -0.52
    POSITIVE LOGITS
     voltages
    0.62
     temperatures
    0.61
    Aiheesta
    0.57
     lower
    0.57
     altitudes
    0.56
    PageContext
    0.55
     equilibrium
    0.55
     frequencies
    0.55
    tagen
    0.55
     higher
    0.54
    Act Density 0.571%

    No Known Activations