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

    Neuronpedia

    INDEX
    Explanations

    to each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .]
    0.40
    trecht
    0.40
     are
    0.40
    3
    0.40
    take
    0.39
     Through
    0.38
     Between
    0.37
    aré
    0.37
    ités
    0.36
    ],
    0.36
    POSITIVE LOGITS
     every
    0.59
     этом
    0.57
     each
    0.57
     this
    0.56
    每一个
    0.56
     каждом
    0.55
     setiap
    0.54
     этой
    0.54
    这个
    0.53
     каждой
    0.50
    Act Density 0.146%

    No Known Activations