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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and structural elements in text

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

    Code, punctuation, or HTML snippets

    np_acts-logits-general · gemini-2.0-flash

    end of code statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tenth
    -0.53
    eqn
    -0.52
     ten
    -0.51
    hexane
    -0.50
     six
    -0.50
    Còn
    -0.49
     Mortimer
    -0.48
    ঞ
    -0.47
     ruote
    -0.47
    ontal
    -0.47
    POSITIVE LOGITS
    StructEnd
    0.88
    <h3>
    0.78
     resourceCulture
    0.73
    లాలు
    0.71
    IonicModule
    0.67
    )++;
    0.65
     Paglinawan
    0.64
    الإنجليزية
    0.63
    ArgumentParser
    0.62
    RenderAtEndOf
    0.61
    Act Density 0.119%

    No Known Activations