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

    Neuronpedia

    INDEX
    Explanations

    references to testing and experimental processes

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

    relating to evaluation and experimentation

    np_acts-logits-general · gemini-2.0-flash

    testing and experiments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.57
    jaardag
    -0.53
     дописавши
    -0.52
    LabelTagHelper
    -0.50
     surla
    -0.47
    WriteAttribute
    -0.47
    ChildScrollView
    -0.46
     незавершена
    -0.44
    Дереккөздер
    -0.43
    ніципа
    -0.42
    POSITIVE LOGITS
     testing
    0.89
     tests
    0.80
     Testing
    0.79
     test
    0.74
    Testing
    0.73
     Tests
    0.71
     TESTING
    0.69
     Test
    0.66
     TestBed
    0.65
    testing
    0.63
    Act Density 0.906%

    No Known Activations