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

    Neuronpedia

    INDEX
    Explanations

    measurements, numbers and dollar amounts

    oai_token-act-pair · gemini-2.0-flash

    measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.54
    <strong>
    -0.48
     t
    -0.47
    t
    -0.45
    .
    -0.45
     T
    -0.45
     El
    -0.42
     O
    -0.42
    Whatever
    -0.42
    et
    -0.41
    POSITIVE LOGITS
    awaiter
    0.95
    =$?
    0.94
     resourceCulture
    0.93
    Datuak
    0.83
    fjspx
    0.83
    +#+#
    0.83
    клопе
    0.82
    rungsseite
    0.82
    CloseOperation
    0.81
    WriteLiteral
    0.80
    Act Density 22.650%

    No Known Activations