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

    Neuronpedia

    INDEX
    Explanations

    structural elements of code, such as class and function declarations

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

    Mathematical notation/formulas

    np_acts-logits-general · gemini-2.0-flash

    math and code contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -1.13
     CreateTagHelper
    -1.02
    <unused51>
    -0.85
    <unused42>
    -0.85
    [@BOS@]
    -0.85
    <pad>
    -0.85
    <unused16>
    -0.84
    <unused17>
    -0.84
    <unused14>
    -0.84
    <unused8>
    -0.84
    POSITIVE LOGITS
    <eos>
    0.36
     himself
    0.33
    ↵↵
    0.32
    -
    0.30
     dict
    0.29
     en
    0.29
     qui
    0.28
     which
    0.27
     R
    0.27
     re
    0.27
    Act Density 0.076%

    No Known Activations