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

    Neuronpedia

    INDEX
    Explanations

    the word "compound" or words relating to the ocean

    oai_token-act-pair · gemini-2.0-flash

    compound, ocean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :✨
    -0.77
     
    -0.77
     the
    -0.76
     a
    -0.73
     C
    -0.71
     S
    -0.71
     Z
    -0.70
     M
    -0.69
     O
    -0.68
     G
    -0.68
    POSITIVE LOGITS
     itſelf
    1.26
     ་་
    1.05
     myſelf
    1.00
     Monfieur
    1.00
     ―――――
    1.00
     pleaſure
    0.96
     Shakspeare
    0.93
     faſt
    0.92
    MessageState
    0.89
     againſt
    0.88
    Act Density 0.532%

    No Known Activations