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

    Neuronpedia

    INDEX
    Explanations

    single quote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.19
    ihnachten
    -0.66
    ParallelGroup
    -0.58
    )_/¯
    -0.57
    šana
    -0.56
     udaler
    -0.56
    ihnachts
    -0.56
    šanās
    -0.56
    oarece
    -0.55
     élevées
    -0.55
    POSITIVE LOGITS
    9
    0.68
    5
    0.57
    3
    0.52
    8
    0.52
    4
    0.51
     Activate
    0.50
    6
    0.49
    sidemargin
    0.49
    7
    0.49
    2
    0.47
    Act Density 0.027%

    No Known Activations