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

    Neuronpedia

    INDEX
    Explanations

    references to proverbs or commonly known sayings

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

    saying "phrase"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.59
     Planner
    -0.54
    лтемелер
    -0.53
     الرياضيه
    -0.52
     Runners
    -0.51
    SBATCH
    -0.51
     utafitiHapana
    -0.51
     onCancelled
    -0.50
    Manbalar
    -0.50
    parsedMessage
    -0.48
    POSITIVE LOGITS
     marins
    0.36
     göm
    0.35
     Geset
    0.35
     Gesetze
    0.33
    ésult
    0.31
     saying
    0.31
     defStyleAttr
    0.31
    言
    0.31
     teorías
    0.31
    \{\\
    0.30
    Act Density 0.022%

    No Known Activations