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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe types or kinds of things

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

    "kind/type of"

    np_acts-logits-general · gemini-2.0-flash

    types and kinds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.69
    fjspx
    -0.67
    Билгалдахарш
    -0.67
    featureID
    -0.64
     autorytatywna
    -0.64
     محفوظة
    -0.63
     volontà
    -0.62
    EDEFAULT
    -0.61
    ThroughAttribute
    -0.61
    Източници
    -0.61
    POSITIVE LOGITS
     thing
    0.67
     scenario
    0.66
     interaction
    0.64
     creature
    0.59
     деятельности
    0.59
     activity
    0.59
     nourishment
    0.58
     situation
    0.58
     arrangement
    0.58
     clientele
    0.57
    Act Density 0.143%

    No Known Activations