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

    Neuronpedia

    INDEX
    Explanations

    obviousness, directness, clarity

    np_acts-logits-general · gemini-2.5-flash-lite

    metadiscourse that emphasizes obviousness, immediacy, or directness—marking statements as clear, straightforward, or self-evident.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     möglicherweise
    0.46
     बचें
    0.39
     besonderen
    0.38
     mysteriously
    0.38
    ྥ
    0.38
     geeignet
    0.36
     considere
    0.36
     দূরে
    0.35
     อาจ
    0.35
     NOT
    0.35
    POSITIVE LOGITS
     obvious
    1.36
     당연
    1.00
     obviously
    0.98
     straightforward
    0.97
     obviamente
    0.93
     ovviamente
    0.90
    obviously
    0.89
     évidemment
    0.87
     évident
    0.86
     oczywiście
    0.86
    Act Density 0.327%

    No Known Activations