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

    Neuronpedia

    INDEX
    Explanations

    underscore-prefixed terms in coding or programming contexts

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

    test and programming operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.61
     queſta
    -0.60
     ſta
    -0.59
    IsMutable
    -0.58
    AutoField
    -0.57
     pleaſure
    -0.56
    السكان
    -0.56
    mybatisplus
    -0.56
    quelize
    -0.56
    AddTagHelper
    -0.55
    POSITIVE LOGITS
    test
    0.53
    _
    0.51
    testing
    0.49
     Künst
    0.43
     testing
    0.43
    Testing
    0.43
     Handbuch
    0.42
     peor
    0.42
    case
    0.42
     Frucht
    0.41
    Act Density 0.002%

    No Known Activations