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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    heroes
    -0.07
    —is
    -0.06
     losses
    -0.06
    مي
    -0.06
     decrypt
    -0.06
     MSE
    -0.06
     maturity
    -0.06
    .avg
    -0.06
     Thế
    -0.06
    	sock
    -0.06
    POSITIVE LOGITS
     облад
    0.07
    .recipe
    0.07
    эт
    0.06
     Environmental
    0.06
     luyện
    0.06
    .setStroke
    0.06
     environmental
    0.06
     ENTRY
    0.06
    _FRONT
    0.06
    _sensor
    0.06
    Act Density 0.000%

    No Known Activations