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

    Neuronpedia

    INDEX
    Explanations

    multiplication symbols and symbols near equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acariy
    0.84
    gdock
    0.71
    überküloz
    0.69
     کریم
    0.69
    𒊬
    0.66
    racción
    0.66
    itabbam
    0.66
    öffentlich
    0.64
    segaretro
    0.64
    鳗
    0.64
    POSITIVE LOGITS
    0.88
     C
    0.81
     *
    0.81
     I
    0.80
     (
    0.80
     L
    0.80
     {
    0.79
     x
    0.79
     +
    0.78
     D
    0.76
    Act Density 0.122%

    No Known Activations