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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    教授
    -0.07
    /service
    -0.07
    .math
    -0.06
     Kevin
    -0.06
     veloc
    -0.06
     DRM
    -0.06
    ジア
    -0.06
     Dom
    -0.06
     Room
    -0.06
    /google
    -0.06
    POSITIVE LOGITS
    _ipv
    0.06
    _multiple
    0.06
    巻
    0.06
    957
    0.06
     Söz
    0.06
     hesab
    0.06
     groupBox
    0.06
     أش
    0.06
    桂
    0.06
    Attack
    0.06
    Act Density 0.050%

    No Known Activations