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

    Neuronpedia

    INDEX
    Explanations

    words related to chemical reactions and processes

    oai_token-act-pair · gemini-2.0-flash

    chemical reactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -1.12
     Reſ
    -1.04
     poffible
    -1.03
     ſtate
    -1.02
     myſelf
    -1.00
     ſever
    -1.00
     houſe
    -0.99
     greateſt
    -0.98
     ſta
    -0.97
     deſt
    -0.97
    POSITIVE LOGITS
     
    0.75
    .
    0.60
    ↵
    0.60
    '
    0.58
     (
    0.58
      
    0.57
    ↵↵
    0.56
     "
    0.56
    (
    0.54
    2
    0.52
    Act Density 5.036%

    No Known Activations