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

    Neuronpedia

    INDEX
    Explanations

    education protocols recovered iPhone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Videos
    0.41
    列
    0.39
     x
    0.39
     plus
    0.38
     кре
    0.38
     +
    0.37
     videolar
    0.37
     sie
    0.37
     cré
    0.37
     videos
    0.36
    POSITIVE LOGITS
     hailing
    0.40
    丁寧
    0.39
    शिक्षा
    0.39
     THEM
    0.39
     onları
    0.38
    )}(\
    0.38
    OLYBDENUM
    0.38
    貽
    0.38
    ेशर
    0.37
     LANC
    0.36
    Act Density 0.000%

    No Known Activations