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

    Neuronpedia

    INDEX
    Explanations

    indications of numbers or statistics

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

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OFDb
    -0.41
    PHI
    -0.35
    eren
    -0.32
    xffffff
    -0.32
    一项
    -0.31
    Mim
    -0.31
    ahn
    -0.31
    PHA
    -0.30
    kömm
    -0.30
    Nah
    -0.30
    POSITIVE LOGITS
    ########.
    0.55
    Gemeinden
    0.52
     nahilalakip
    0.50
    tvguidetime
    0.49
    invokeLater
    0.48
    yonel
    0.48
     amitié
    0.47
    EndContext
    0.45
     maternidade
    0.45
     gepubliceerd
    0.44
    Act Density 0.074%

    No Known Activations