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

    Neuronpedia

    INDEX
    Explanations

    phrases related to system operations and functionality

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

    preceding quantities or sizes

    np_acts-logits-general · gemini-2.0-flash

    larger quantities or comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.60
     everyday
    -0.56
    everyday
    -0.56
     multiplicity
    -0.55
     Wiktionnaire
    -0.53
    iduous
    -0.52
     Everyday
    -0.51
    erdere
    -0.51
     Minor
    -0.49
    MULTIPLE
    -0.49
    POSITIVE LOGITS
     larger
    0.77
     bigger
    0.74
     big
    0.73
     grand
    0.71
    big
    0.67
     main
    0.67
     overarching
    0.64
     rarer
    0.64
     rare
    0.63
    larger
    0.63
    Act Density 0.632%

    No Known Activations