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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    祖
    -0.07
     Rodrig
    -0.06
    _FINAL
    -0.06
    _quotes
    -0.06
     misd
    -0.06
     bardzo
    -0.06
    _widget
    -0.06
     �
    -0.06
     recebe
    -0.06
    Pressed
    -0.06
    POSITIVE LOGITS
     Krak
    0.07
    されて
    0.06
    เทศ
    0.06
     chặt
    0.06
    (-
    0.06
    ^{-
    0.06
     Mumbai
    0.06
     infectious
    0.06
    .www
    0.06
    ask
    0.06
    Act Density 0.089%

    No Known Activations