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

    Neuronpedia

    INDEX
    Explanations

    worse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ware
    -0.07
    )는
    -0.06
     mirrors
    -0.06
     Transformers
    -0.06
     Keeps
    -0.06
    VERY
    -0.06
    ีอ
    -0.06
     illuminate
    -0.06
    .PRO
    -0.06
     WTO
    -0.06
    POSITIVE LOGITS
     completion
    0.07
    방
    0.06
     diameter
    0.06
    见
    0.06
    ständ
    0.06
    分析
    0.06
     sourcing
    0.06
     Palette
    0.06
     firewall
    0.06
     EDM
    0.06
    Act Density 0.001%

    No Known Activations