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

    Neuronpedia

    INDEX
    Explanations

    photo captions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    كار
    -0.07
    .time
    -0.07
     outrage
    -0.07
     colleg
    -0.06
    еного
    -0.06
     sled
    -0.06
    uib
    -0.06
     перепис
    -0.06
    디
    -0.06
    _HDR
    -0.06
    POSITIVE LOGITS
    entlich
    0.07
     Mısır
    0.06
    Steps
    0.06
     Pablo
    0.06
    登場
    0.06
    _remaining
    0.06
    aken
    0.06
     Cette
    0.06
    .resolve
    0.06
    -settings
    0.06
    Act Density 0.015%

    No Known Activations