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

    Neuronpedia

    INDEX
    Explanations

    event status messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     désigne
    0.46
     '(
    0.43
     ellipses
    0.42
    शत
    0.42
     относятся
    0.42
     isTestSource
    0.41
     จง
    0.41
     splitpos
    0.41
     détermine
    0.40
     heuristics
    0.40
    POSITIVE LOGITS
     got
    0.51
     reached
    0.49
     arrived
    0.45
    Reached
    0.45
     recibieron
    0.44
     recibió
    0.43
    caught
    0.43
     وصلت
    0.42
     caught
    0.42
    탔
    0.42
    Act Density 0.079%

    No Known Activations