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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phenomenon
    -0.07
     scn
    -0.06
    unned
    -0.06
    ोक
    -0.06
    cam
    -0.06
     `;↵
    -0.06
     Rigidbody
    -0.06
    真
    -0.06
    DataFrame
    -0.06
     rentals
    -0.06
    POSITIVE LOGITS
    _standard
    0.08
     Peyton
    0.07
     SN
    0.06
     debilitating
    0.06
     Dolphins
    0.06
     Smarty
    0.06
     чого
    0.06
    掉
    0.06
    ////////////////////////////////
    0.06
    buquerque
    0.06
    Act Density 0.023%

    No Known Activations