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

    Neuronpedia

    INDEX
    Explanations

    references to various model classes in programming or software development contexts

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

    models and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rheumat
    -0.48
    ruptedException
    -0.47
    aspectj
    -0.47
    IntoConstraints
    -0.45
    SIGINT
    -0.45
     sqlSession
    -0.44
    vacy
    -0.44
    甚
    -0.44
    Preamble
    -0.44
    addCriterion
    -0.43
    POSITIVE LOGITS
    models
    2.52
    Models
    1.58
     Models
    1.28
     models
    1.15
     MODELS
    1.13
    modelos
    0.92
     modelos
    0.80
    Modelos
    0.79
    modelle
    0.77
     Modelle
    0.75
    Act Density 0.001%

    No Known Activations