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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "instance" and related terms

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

    instance examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Governing
    -0.50
    Selamat
    -0.50
    legungen
    -0.48
    ambién
    -0.48
    ByEmail
    -0.47
    rugby
    -0.46
    Ethical
    -0.45
    BACA
    -0.45
    hematical
    -0.44
    以下是
    -0.42
    POSITIVE LOGITS
    instance
    1.63
     instance
    1.44
     Instance
    1.40
    Instance
    1.39
    INSTANCE
    1.18
     INSTANCE
    1.09
    getInstance
    1.08
     Instances
    1.08
     instances
    1.03
    instances
    0.99
    Act Density 0.012%

    No Known Activations