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

    Neuronpedia

    INDEX
    Explanations

    references to singular items or concepts

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

    Sentences containing "one"

    np_acts-logits-general · gemini-2.0-flash

    referring to a specific instance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ly
    -0.66
    tly
    -0.57
    pande
    -0.52
     SK
    -0.51
    oly
    -0.50
    ment
    -0.49
    enteuer
    -0.49
     }}{\
    -0.49
    vin
    -0.48
    fully
    -0.48
    POSITIVE LOGITS
     antaranya
    0.89
     nahilalakip
    0.89
    SBATCH
    0.86
    Geplaatst
    0.84
     चीज़ों
    0.82
     виправивши
    0.81
     للمعارف
    0.79
     '\\;'
    0.79
    IContainer
    0.79
     &___
    0.79
    Act Density 0.134%

    No Known Activations