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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _estimate
    -0.07
     či
    -0.07
    ，用
    -0.06
    uda
    -0.06
     bý
    -0.06
    	a
    -0.06
    이에
    -0.06
    assy
    -0.06
    ocracy
    -0.06
     vocalist
    -0.06
    POSITIVE LOGITS
    Austin
    0.06
    illisecond
    0.06
     onload
    0.06
     frees
    0.06
    riteln
    0.06
    нем
    0.06
     CURL
    0.06
     ops
    0.06
     geliş
    0.06
    .cm
    0.06
    Act Density 0.010%

    No Known Activations