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

    Neuronpedia

    INDEX
    Explanations

    file paths and code snippets

    oai_token-act-pair · gemini-2.0-flash

    home

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -0.95
     Efq
    -0.93
     Monfieur
    -0.89
     betweenstory
    -0.89
     itſelf
    -0.85
     photolibrary
    -0.81
     Cæsar
    -0.79
     ―――――
    -0.76
     reft
    -0.74
     purpoſe
    -0.74
    POSITIVE LOGITS
    <bos>
    0.57
     dne
    0.40
    <eos>
    0.39
    l
    0.38
    CreateMap
    0.38
     bek
    0.38
    setViewName
    0.37
     les
    0.37
    wość
    0.37
    no
    0.36
    Act Density 2.754%

    No Known Activations