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

    Neuronpedia

    INDEX
    Explanations

    references to fields of invention or classification

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

    "Field of the Invention" phrases

    np_acts-logits-general · gemini-2.0-flash

    Field of the Invention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    polated
    -0.61
     termica
    -0.59
    wohnt
    -0.59
     Maddox
    -0.58
     Knud
    -0.58
    tled
    -0.56
    polation
    -0.56
     heck
    -0.54
    lija
    -0.53
    ../../
    -0.53
    POSITIVE LOGITS
     getField
    1.02
     fields
    0.79
     Fields
    0.76
    fields
    0.75
    Fields
    0.73
     FIELDS
    0.73
     Field
    0.72
    FIELDS
    0.69
     FIELD
    0.69
    ThroughAttribute
    0.68
    Act Density 0.164%

    No Known Activations