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

    Neuronpedia

    INDEX
    Explanations

    taking turns placing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     COULD
    0.46
     especific
    0.46
     okaza
    0.45
     אני
    0.43
    legant
    0.42
     предлага
    0.42
    rov
    0.42
    นั้น
    0.41
    ok
    0.41
    ros
    0.41
    POSITIVE LOGITS
     narcot
    0.55
     Mön
    0.53
     Tripura
    0.52
     Esch
    0.52
     traw
    0.51
     tetragonal
    0.50
    ürzt
    0.50
     Pache
    0.49
     cirrhosis
    0.49
     vért
    0.49
    Act Density 0.049%

    No Known Activations