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

    Neuronpedia

    INDEX
    Explanations

    Super

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.67
    ❉
    -0.64
    帖最后由
    -0.61
    ➯
    -0.59
     HasFactory
    -0.57
     Савезне
    -0.51
     correctes
    -0.51
    ihnachten
    -0.51
    ocities
    -0.49
    Uninitialized
    -0.49
    POSITIVE LOGITS
    MessageOf
    0.51
    Incluso
    0.51
     تضيفلها
    0.51
    прочем
    0.50
     Daß
    0.50
    let
    0.48
    IntoConstraints
    0.47
    hause
    0.47
     때문
    0.47
    Even
    0.46
    Act Density 0.028%

    No Known Activations