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

    Neuronpedia

    INDEX
    Explanations

    assertions related to economic costs and comparing expenses

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

    "average/typical" or related terms

    np_acts-logits-general · gemini-2.0-flash

    average and typical values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sterious
    -0.62
    Sonstiges
    -0.60
    引き続き
    -0.59
    reszcie
    -0.59
     Connectez
    -0.57
    ännande
    -0.54
     Continues
    -0.54
    Sempre
    -0.54
     selanjutnya
    -0.54
    一会
    -0.53
    POSITIVE LOGITS
     average
    1.58
     typical
    1.42
    average
    1.34
    Typical
    1.26
     Typical
    1.25
    Average
    1.24
     promedio
    1.21
     Average
    1.17
     durchschnitt
    1.15
     AVERAGE
    1.14
    Act Density 0.484%

    No Known Activations