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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to contests and rankings, including the results of polls.

    oai_token-act-pair · gemini-2.0-flash

    comparisons and results

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.73
    DockStyle
    -0.70
    Personendaten
    -0.59
    ="'.$
    -0.59
     ligiloj
    -0.57
    曖昧さ回避
    -0.57
     незавершена
    -0.57
    nhung
    -0.57
    pannt
    -0.57
     myſelf
    -0.57
    POSITIVE LOGITS
     with
    1.14
    with
    0.90
     avec
    0.88
     với
    0.81
    With
    0.81
     With
    0.81
     WITH
    0.76
     dengan
    0.75
    avec
    0.68
     boasting
    0.64
    Act Density 1.737%

    No Known Activations