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

    Neuronpedia

    INDEX
    Explanations

    XML element definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     learnt
    0.40
    ='';
    0.39
    च्युअल
    0.39
    𝓐
    0.38
    ्राट
    0.38
    ఖా
    0.38
    ्यर
    0.37
    Mys
    0.37
     smoker
    0.37
    驴
    0.37
    POSITIVE LOGITS
    [
    0.41
    Tres
    0.39
     Kinect
    0.38
     Nation
    0.38
     [
    0.38
     Tres
    0.38
     Two
    0.36
    過程中
    0.36
    alla
    0.35
     Three
    0.35
    Act Density 0.001%

    No Known Activations