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

    Neuronpedia

    INDEX
    Explanations

    items in enumerated lists

    oai_token-act-pair · gemini-2.0-flash

    say ") character"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الرياضيه
    -1.01
     Efq
    -0.88
    Personendaten
    -0.87
    ItemBackground
    -0.77
    mặt
    -0.70
    makeConstraints
    -0.70
     समीक्षक
    -0.69
     تضيفلها
    -0.69
    ^(@)
    -0.68
     myſelf
    -0.68
    POSITIVE LOGITS
    )}-
    0.87
    )}+
    0.80
    )}+\
    0.78
    }])
    0.76
    }}_
    0.74
    )}$
    0.71
    }}_{
    0.68
    )}_{
    0.68
    }}-
    0.66
    }}}{
    0.65
    Act Density 5.079%

    No Known Activations