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

    Neuronpedia

    INDEX
    Explanations

    references to chemical compounds

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

    compound

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.77
     erſt
    -0.66
     Geiſt
    -0.66
     laſſen
    -0.66
    ſelben
    -0.65
     ainfi
    -0.64
    <pad>
    -0.64
    <unused8>
    -0.63
    <unused3>
    -0.63
    [@BOS@]
    -0.63
    POSITIVE LOGITS
     compound
    1.13
     Compound
    1.11
    Compound
    1.00
     COMPOUND
    0.90
     compounds
    0.90
    compound
    0.88
     Compounds
    0.78
     compounding
    0.70
     compounded
    0.67
     COMPOUNDS
    0.64
    Act Density 0.009%

    No Known Activations