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

    Neuronpedia

    INDEX
    Explanations

    instances of frequency-related terms

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

    often times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.62
    twimg
    -0.57
     Autorizaciones
    -0.54
     autorytatywna
    -0.54
     always
    -0.54
    always
    -0.54
    IVEREF
    -0.53
     sempre
    -0.52
     constantly
    -0.51
    ">//
    -0.51
    POSITIVE LOGITS
     المعيارى
    0.64
    KommentareTeilen
    0.61
     justru
    0.54
     бывает
    0.52
     kasus
    0.47
     overlooked
    0.45
     malah
    0.45
     bowiem
    0.45
     bý
    0.43
    情况下
    0.43
    Act Density 0.033%

    No Known Activations