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

    Neuronpedia

    INDEX
    Explanations

    separation and communication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exiting
    -0.07
     بر
    -0.07
    .What
    -0.06
     timeStamp
    -0.06
    ,d
    -0.06
    _fr
    -0.06
    sounds
    -0.06
    Exiting
    -0.06
    (span
    -0.06
     PC
    -0.06
    POSITIVE LOGITS
    нолог
    0.06
    ENN
    0.06
    roy
    0.06
     Yellowstone
    0.06
    雑
    0.06
    怀
    0.06
    listed
    0.06
    вою
    0.06
     Meadows
    0.06
     attitudes
    0.06
    Act Density 0.058%

    No Known Activations