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

    Neuronpedia

    INDEX
    Explanations

    latex code related to kernels and images of linear transformations

    oai_token-act-pair · gemini-2.0-flash

    ker

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WEBPACK
    -0.73
     Whit
    -0.51
     per
    -0.49
     round
    -0.47
     En
    -0.46
     mid
    -0.46
     mon
    -0.45
     en
    -0.44
    ː
    -0.44
     return
    -0.43
    POSITIVE LOGITS
     Efq
    0.94
     raiſ
    0.91
     Majefty
    0.88
     myſelf
    0.86
     Cæsar
    0.84
     Monfieur
    0.84
     Jefus
    0.84
     Anſ
    0.82
     StatefulWidget
    0.80
     Chrif
    0.78
    Act Density 2.353%

    No Known Activations