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

    Neuronpedia

    INDEX
    Explanations

    logical connectors and reasoning cues in argumentative or explanatory text

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

    cannot or unable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تانيه
    -0.39
     altern
    -0.38
    enterOuterAlt
    -0.38
     snippetHide
    -0.37
    twimg
    -0.37
    ⓧ
    -0.35
     "]";
    -0.33
    Portale
    -0.33
    "]();
    -0.33
    keyColumn
    -0.32
    POSITIVE LOGITS
     unable
    0.68
     Cannot
    0.68
     Unable
    0.67
    impossible
    0.65
    Unable
    0.64
     impossível
    0.64
    Cannot
    0.63
     inability
    0.63
    Impossible
    0.63
     impossible
    0.63
    Act Density 0.124%

    No Known Activations