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

    Neuronpedia

    INDEX
    Explanations

    Research and technical reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -0.91
     raiſ
    -0.88
     myſelf
    -0.87
     Monfieur
    -0.85
    ConstraintMaker
    -0.85
     uſed
    -0.82
    ſelves
    -0.78
    NUMX
    -0.77
     Theſe
    -0.77
     itſelf
    -0.77
    POSITIVE LOGITS
    yla
    0.59
    ,
    0.57
    o
    0.52
    MLLoader
    0.51
    น
    0.50
     habis
    0.49
    /
    0.48
     I
    0.47
    &
    0.47
    꿀
    0.47
    Act Density 0.000%

    No Known Activations