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

    Neuronpedia

    INDEX
    Explanations

    special formatting and structure in text, such as citations and mathematical notations

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

    Citation endings followed by a period

    np_acts-logits-general · gemini-2.0-flash

    scientific paper titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    usermodel
    -0.60
     laſt
    -0.56
     saddest
    -0.55
    Скачать
    -0.55
    setViewportView
    -0.54
     Credo
    -0.54
    TabIndex
    -0.54
     astronomer
    -0.54
     通常
    -0.53
    bootstrapcdn
    -0.53
    POSITIVE LOGITS
     Effects
    0.72
     effects
    0.71
    Effects
    0.70
     influence
    0.69
     The
    0.69
     comparison
    0.68
    Comparison
    0.68
     An
    0.68
     Effect
    0.67
    effects
    0.66
    Act Density 0.406%

    No Known Activations