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

    Neuronpedia

    INDEX
    Explanations

    Article beginnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <eos>
    -0.67
    ,
    -0.52
     (
    -0.51
    are
    -0.51
    AxisAlignment
    -0.44
     eller
    -0.43
     og
    -0.42
     oder
    -0.42
     hoặc
    -0.41
     or
    -0.40
    POSITIVE LOGITS
     myſelf
    1.06
     houſe
    1.00
     itſelf
    0.93
     againſt
    0.91
     Houſe
    0.89
     preſent
    0.88
     himſelf
    0.87
     pleaſure
    0.83
     ſaid
    0.83
     Efq
    0.82
    Act Density 0.001%

    No Known Activations