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

    Neuronpedia

    INDEX
    Explanations

    terms related to instructions or actions taken in a procedural context

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

    measures or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Numerade
    -0.48
     kyllä
    -0.42
    fires
    -0.42
    MongoClient
    -0.41
    metz
    -0.41
    ########.
    -0.39
    umes
    -0.39
    Mat
    -0.39
     الرياضيه
    -0.39
    Marcia
    -0.38
    POSITIVE LOGITS
     futurs
    0.53
     zukünf
    0.52
    ViewFeatures
    0.52
     future
    0.49
    FontOfSize
    0.49
     künf
    0.48
    AnchorStyles
    0.47
    MLLoader
    0.47
     StringTokenizer
    0.46
     futuros
    0.45
    Act Density 0.067%

    No Known Activations