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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of disbelief or surprise

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

    following "never," "not," or negative contractions

    np_acts-logits-general · gemini-2.0-flash

    realization after not knowing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pulumi
    -0.61
     SIMBAD
    -0.61
    (||
    -0.55
     ISNI
    -0.55
    antMatchers
    -0.54
    )";
    -0.54
    runApp
    -0.53
     Simplemente
    -0.51
    **
    -0.51
     Unsc
    -0.51
    POSITIVE LOGITS
     realize
    1.23
     realise
    1.12
     realizes
    1.06
     realized
    1.06
     realizing
    1.03
     realised
    0.99
     realising
    0.96
     realises
    0.95
     realization
    0.88
     notice
    0.85
    Act Density 0.178%

    No Known Activations