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

    Neuronpedia

    INDEX
    Explanations

    phrases referencing time, particularly relating to weeks and years

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

    past year, weeks, months, decade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     späteren
    -0.47
     участь
    -0.44
     Later
    -0.41
     gemeint
    -0.41
     itinéraires
    -0.40
    Карьера
    -0.39
     amanhã
    -0.39
    ardia
    -0.39
    auw
    -0.39
     Cleaning
    -0.39
    POSITIVE LOGITS
    ſelf
    0.54
    دانشنامهٔ
    0.47
     FetchType
    0.45
    newArrayList
    0.41
    tagext
    0.41
    parsedMessage
    0.40
     Preferencias
    0.40
    ngdoc
    0.40
     kasarigan
    0.39
    wapV
    0.39
    Act Density 0.025%

    No Known Activations