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

    Neuronpedia

    INDEX
    Explanations

    programming code and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IActionResult
    -0.84
    Beij
    -0.81
     stratég
    -0.77
     های
    -0.77
    ({},
    -0.77
    ıştır
    -0.76
    igrafi
    -0.75
     Vra
    -0.75
    bsp
    -0.72
    ［
    -0.72
    POSITIVE LOGITS
     now
    1.14
    now
    0.87
     сейчас
    0.85
     x
    0.84
    LANE
    0.84
    学び
    0.84
     u
    0.82
     NOW
    0.80
     今
    0.80
    poss
    0.79
    Act Density 0.006%

    No Known Activations