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

    Neuronpedia

    INDEX
    Explanations

    let

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     let
    -0.66
     me
    -0.59
     her
    -0.48
     Markle
    -0.48
     Me
    -0.45
    ]--;
    -0.45
    TERY
    -0.44
     Let
    -0.44
     his
    -0.44
    出版年
    -0.44
    POSITIVE LOGITS
    SerializedSize
    0.67
    IntoConstraints
    0.64
     Houſe
    0.62
    TypedDataSet
    0.61
     للمعارف
    0.61
    ajā
    0.60
     Silurian
    0.59
     Francus
    0.59
     Theſe
    0.59
     mijne
    0.58
    Act Density 0.243%

    No Known Activations