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

    Neuronpedia

    INDEX
    Explanations

    mentions of weight in pounds

    oai_token-act-pair · gemini-2.0-flash

    pounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.76
     AssemblyCompany
    -0.75
    BufferException
    -0.70
    NameInMap
    -0.69
    ExtendWith
    -0.68
    parsedMessage
    -0.67
     marchio
    -0.66
    ContextCompat
    -0.65
    XmlAccessType
    -0.65
    igshid
    -0.64
    POSITIVE LOGITS
     Monfieur
    0.74
    <bos>
    0.70
     "");
    0.70
     Theſe
    0.70
    }';
    0.66
    "';
    0.65
     pleaſure
    0.65
    "।
    0.64
    }');
    0.64
     Eury
    0.63
    Act Density 0.448%

    No Known Activations