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

    Neuronpedia

    INDEX
    Explanations

    define

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    120
    -0.07
     Winter
    -0.07
    	Request
    -0.07
    Acceleration
    -0.07
     Amsterdam
    -0.07
     bike
    -0.07
    Request
    -0.07
    염
    -0.07
    spd
    -0.06
    Detroit
    -0.06
    POSITIVE LOGITS
     |:
    0.08
     Wiley
    0.06
     tol
    0.06
    ोजन
    0.06
    incipal
    0.06
     إذا
    0.06
    .Sub
    0.06
     poking
    0.06
    пр
    0.06
    ิหาร
    0.06
    Act Density 0.015%

    No Known Activations