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

    Neuronpedia

    INDEX
    Explanations

    specific expressions of gratitude

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

    Sentences ending in a period

    np_acts-logits-general · gemini-2.0-flash

    . followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.87
    󠁢
    -0.79
    ArgsConstructor
    -0.73
     '{@
    -0.71
    NUMX
    -0.70
    ="@+
    -0.68
    ---*/
    -0.67
    paramref
    -0.65
    帖最后由
    -0.64
     RoutedEventArgs
    -0.64
    POSITIVE LOGITS
     The
    0.98
    The
    0.85
    ↵↵
    0.84
     This
    0.83
     ...
    0.82
     They
    0.78
    A
    0.74
    They
    0.74
     We
    0.74
     It
    0.73
    Act Density 0.152%

    No Known Activations