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

    Neuronpedia

    INDEX
    Explanations

    code indicating class inheritance in programming

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

    class extension in programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſever
    -0.69
     ſte
    -0.67
     ſch
    -0.67
     Majefty
    -0.63
     ſta
    -0.63
     pleaſure
    -0.63
     canst
    -0.62
     faſt
    -0.62
     itſelf
    -0.61
     Anſ
    -0.60
    POSITIVE LOGITS
     extends
    1.41
    extends
    1.28
     extend
    1.01
     extending
    0.88
     Extend
    0.85
     Extending
    0.82
    extend
    0.81
     extended
    0.76
     Extended
    0.72
     extiende
    0.64
    Act Density 0.004%

    No Known Activations