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

    Neuronpedia

    INDEX
    Explanations

    output by agent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conectados
    0.54
     oktober
    0.52
    спе
    0.52
     marchio
    0.52
    罫
    0.52
     collegamento
    0.51
     cujo
    0.51
    chlor
    0.50
     lesquels
    0.49
     които
    0.49
    POSITIVE LOGITS
     creates
    0.58
    IDUAL
    0.57
     finds
    0.55
     becomes
    0.55
    GAD
    0.53
     بواسطة
    0.53
     gets
    0.52
    iveness
    0.52
     Pert
    0.51
     оказыва
    0.51
    Act Density 0.000%

    No Known Activations