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

    Neuronpedia

    INDEX
    Explanations

    record breaking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pihak
    1.16
    ون
    1.02
     natoque
    1.01
     shine
    1.00
    ć
    1.00
    ようになりました
    0.96
     inex
    0.96
     ionizing
    0.95
     única
    0.95
     sparkle
    0.94
    POSITIVE LOGITS
    お
    1.10
    おそらく
    1.04
    പ്പെടുത്ത
    1.00
    از
    0.99
     تعدى
    0.95
     récord
    0.94
    dade
    0.93
    cylinder
    0.92
    ο
    0.91
     във
    0.91
    Act Density 0.040%

    No Known Activations