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

    Neuronpedia

    INDEX
    Explanations

    numerical values, especially those related to measurements and time

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

    quantities and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Signalez
    -0.31
    хьтан
    -0.31
    oa̍t
    -0.30
     estructural
    -0.30
     mourut
    -0.28
     Савезне
    -0.28
     répé
    -0.28
    kijken
    -0.28
     alimentaires
    -0.28
     fédé
    -0.27
    POSITIVE LOGITS
    AddTagHelper
    0.76
    webElement
    0.70
    󠁢
    0.63
     Normdatei
    0.60
    aderie
    0.59
    neurial
    0.58
    tificates
    0.58
    pherds
    0.58
    phal
    0.58
    half
    0.58
    Act Density 0.043%

    No Known Activations