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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Way
    -1.31
     Majefty
    -1.29
     Way
    -1.22
    ſelves
    -1.21
     purpoſe
    -1.17
    ſelf
    -1.16
     Houſe
    -1.13
     Reſ
    -1.11
     pleaſure
    -1.11
     Efq
    -1.08
    POSITIVE LOGITS
     min
    0.65
     na
    0.56
     TODO
    0.52
    getDeclared
    0.52
     den
    0.51
     max
    0.51
     por
    0.50
     sus
    0.50
    筋
    0.50
     bot
    0.50
    Act Density 0.224%

    No Known Activations