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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating a review or judgement of something

    oai_token-act-pair · gemini-2.0-flash

    adjective suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -0.98
     Majefty
    -0.98
    <bos>
    -0.92
     myſelf
    -0.82
     Chriftian
    -0.82
    ſelves
    -0.79
    sprzedam
    -0.79
     whoſe
    -0.77
     Jefus
    -0.77
     Monfieur
    -0.77
    POSITIVE LOGITS
    出版年
    0.71
     useEffect
    0.69
    ren
    0.64
    M
    0.63
    O
    0.62
     dAtA
    0.62
    ir
    0.61
    ig
    0.61
     konk
    0.60
    B
    0.60
    Act Density 2.659%

    No Known Activations