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

    Neuronpedia

    INDEX
    Explanations

    numerical values or references to time intervals

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

    quantifying duration or quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     firebaseConfig
    -0.33
    Географиясе
    -0.32
     betweenstory
    -0.31
    ChildIndex
    -0.30
     gevolg
    -0.30
     plötzlich
    -0.30
    mpä
    -0.29
    iligung
    -0.29
     ternyata
    -0.29
     efectivamente
    -0.29
    POSITIVE LOGITS
    expandindo
    0.84
     brief
    0.66
     brie
    0.60
     zwiſchen
    0.60
    Brief
    0.59
    帖最后由
    0.58
    brief
    0.58
     concise
    0.57
     好文分享
    0.56
     thiệu
    0.55
    Act Density 0.161%

    No Known Activations