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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     asserted
    -0.06
    AXB
    -0.06
    ุญ
    -0.06
     swords
    -0.06
     Серед
    -0.06
     Builders
    -0.06
    .wav
    -0.06
     Над
    -0.06
    Hat
    -0.06
     Quincy
    -0.06
    POSITIVE LOGITS
    script
    0.06
     dopad
    0.06
    .MinValue
    0.06
    。我
    0.06
    Trial
    0.06
    (sockfd
    0.06
     podría
    0.06
     багать
    0.06
    ene
    0.06
     уже
    0.06
    Act Density 0.017%

    No Known Activations