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

    Neuronpedia

    INDEX
    Explanations

    references to data analysis and manuscript preparation processes

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

    Follows punctuation, symbols, or special characters

    np_acts-logits-general · gemini-2.0-flash

    numeric and symbolic characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.56
     blessé
    -0.53
     resté
    -0.51
     refusé
    -0.50
     riduzione
    -0.49
     décédé
    -0.48
     commerciali
    -0.48
    AlterField
    -0.47
     engagé
    -0.46
     religieux
    -0.46
    POSITIVE LOGITS
    tonsoft
    0.81
     protoimpl
    0.72
    RegressionTest
    0.72
    oneofs
    0.66
    TagHelper
    0.65
    GraphicsUnit
    0.65
    uxxxx
    0.63
     الحره
    0.60
    enderror
    0.59
    ValueStyle
    0.58
    Act Density 0.260%

    No Known Activations