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

    Neuronpedia

    INDEX
    Explanations

    advice and judgement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    伤
    -0.07
    .txt
    -0.06
     unordered
    -0.06
    .quit
    -0.06
     Ảnh
    -0.06
    _makeConstraints
    -0.06
    (ph
    -0.06
     uncompressed
    -0.06
     lässt
    -0.06
    Seven
    -0.06
    POSITIVE LOGITS
    trust
    0.07
     eyed
    0.07
    윤
    0.07
     Recommend
    0.06
     Bern
    0.06
    emade
    0.06
    ROY
    0.06
     glor
    0.06
    lepší
    0.06
    ेय
    0.06
    Act Density 0.102%

    No Known Activations