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

    Neuronpedia

    INDEX
    Explanations

    coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.53
    og
    0.52
    و
    0.47
    هداف
    0.46
    osch
    0.46
     чолові
    0.45
    Year
    0.45
    obi
    0.44
    rafish
    0.44
    ”،
    0.43
    POSITIVE LOGITS
     numai
    0.54
     není
    0.53
     beim
    0.52
     potion
    0.52
     nitrous
    0.51
     prema
    0.50
     după
    0.49
    íp
    0.49
     läuft
    0.48
     tappa
    0.48
    Act Density 0.001%

    No Known Activations