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

    Neuronpedia

    INDEX
    Explanations

    references to espionage and chemical attacks

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

    poisons, toxins, and sprays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.60
    Pautan
    -0.43
     AssemblyCulture
    -0.42
    awtextra
    -0.41
    assertAll
    -0.40
     meubles
    -0.40
     FishBase
    -0.40
     tež
    -0.40
    resizingMask
    -0.40
    }{*}{
    -0.38
    POSITIVE LOGITS
     poisoning
    0.60
     poison
    0.59
    poison
    0.57
     poisoned
    0.57
     Poison
    0.52
     contamination
    0.52
    Poison
    0.51
     sprayed
    0.50
     grenade
    0.50
     contaminated
    0.47
    Act Density 0.009%

    No Known Activations