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

    Neuronpedia

    INDEX
    Explanations

    conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Union
    -0.07
    Tracks
    -0.06
    inals
    -0.06
    nio
    -0.06
    700
    -0.06
     Saturday
    -0.06
    无法
    -0.06
    _attachment
    -0.06
    (option
    -0.06
    Wednesday
    -0.06
    POSITIVE LOGITS
    '=>
    0.07
     слаб
    0.07
     Rousse
    0.06
    .localPosition
    0.06
    #ab
    0.06
     tabPage
    0.06
     pageTitle
    0.06
    ’es
    0.06
    ])[
    0.06
     kay
    0.06
    Act Density 0.028%

    No Known Activations