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

    Neuronpedia

    INDEX
    Explanations

    terms related to comparisons or distinctions within a context

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

    different gaseous, occurring at, not mention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.67
    <h1>
    -0.56
    I
    -0.53
    ↵↵
    -0.51
    <h2>
    -0.49
    #
    -0.48
    import
    -0.48
    <eos>
    -0.48
    <
    -0.48
    //
    -0.48
    POSITIVE LOGITS
    KommentareTeilen
    0.77
     myſelf
    0.76
     Theſe
    0.74
     ब्रेकडाउन
    0.71
    ConstraintMaker
    0.71
    MLLoader
    0.70
    WaitGroup
    0.65
    évaluateur
    0.65
    rungsseite
    0.65
    DockStyle
    0.65
    Act Density 0.066%

    No Known Activations