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

    Neuronpedia

    INDEX
    Explanations

    online content engagement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    误
    -0.07
    话
    -0.06
    础
    -0.06
    ους
    -0.06
     России
    -0.06
     المس
    -0.06
     Raider
    -0.05
    けれど
    -0.05
    那里
    -0.05
     Ten
    -0.05
    POSITIVE LOGITS
    _integer
    0.07
    […
    0.07
     surprise
    0.06
    -за
    0.06
     enumerate
    0.06
     hath
    0.06
     -------------
    0.06
    /mit
    0.06
     dez
    0.06
    _AdjustorThunk
    0.06
    Act Density 0.036%

    No Known Activations