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

    Neuronpedia

    INDEX
    Explanations

    variable and target

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hyper
    0.70
    ierung
    0.69
     общественных
    0.69
    AN
    0.68
     het
    0.68
     cả
    0.68
    siniz
    0.68
    Changing
    0.68
     xét
    0.67
    Here
    0.66
    POSITIVE LOGITS
    تدائي
    0.88
     corneal
    0.71
     resorption
    0.70
     axles
    0.70
    差别
    0.69
     glycolysis
    0.69
     तत्वा
    0.69
     centrifugation
    0.68
    umpul
    0.68
     flexion
    0.68
    Act Density 0.001%

    No Known Activations