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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     i
    -1.33
     u
    -0.80
     viz
    -0.75
     ie
    -0.65
     I
    -0.63
     t
    -0.60
     August
    -0.54
     um
    -0.52
     y
    -0.49
     k
    -0.49
    POSITIVE LOGITS
     myſelf
    1.24
     purpoſe
    1.22
     ſche
    1.16
     pleaſure
    1.15
     houſe
    1.13
     ſever
    1.09
     itſelf
    1.09
     juſ
    1.07
     uſe
    1.04
     Majefty
    1.01
    Act Density 0.075%

    No Known Activations