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

    Neuronpedia

    INDEX
    Explanations

    court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Conversation
    -0.08
    Tower
    -0.07
    itted
    -0.07
    -end
    -0.06
    -ios
    -0.06
    _capacity
    -0.06
    ripp
    -0.06
    _press
    -0.06
    _OF
    -0.06
    leri
    -0.06
    POSITIVE LOGITS
    .Asset
    0.07
     khả
    0.07
     apologies
    0.06
     تنظ
    0.06
    \/\/
    0.06
     Spoon
    0.06
     admir
    0.06
    ，则
    0.06
    ****************************************************************************
    0.06
     основі
    0.06
    Act Density 0.026%

    No Known Activations