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

    Neuronpedia

    INDEX
    Explanations

    the last name "Hardy", with some tolerance for typos

    oai_token-act-pair · gemini-2.0-flash

    academic citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.35
     itſelf
    -1.16
     chofe
    -1.09
     Jefus
    -1.09
     myſelf
    -1.08
     houſe
    -0.98
     fhew
    -0.96
     whoſe
    -0.96
     Anſ
    -0.95
     Houſe
    -0.95
    POSITIVE LOGITS
    <eos>
    0.58
     Ho
    0.52
     me
    0.52
    ↵
    0.51
     the
    0.51
    -
    0.50
     do
    0.50
     here
    0.50
    '
    0.50
     Do
    0.49
    Act Density 2.325%

    No Known Activations