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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    numerusform
    -0.57
    neurial
    -0.55
     suivante
    -0.52
     ſhould
    -0.50
    från
    -0.49
     connues
    -0.49
     whoſe
    -0.49
    GAG
    -0.48
     connus
    -0.47
    OfWork
    -0.47
    POSITIVE LOGITS
    )):
    0.71
    }]
    0.69
    __':
    0.68
    '):
    0.66
    })();
    0.64
    }],
    0.62
    ValueStyle
    0.61
    "):
    0.60
    adaptiveStyles
    0.60
    ]}"
    0.58
    Act Density 12.272%

    No Known Activations