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

    Neuronpedia

    INDEX
    Explanations

    transport routes and directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Idani
    0.44
    ਨ੍ਹਾਂ
    0.42
    savefig
    0.39
    引擎
    0.38
    पणे
    0.37
    打造
    0.37
    avkh
    0.37
     बीटल
    0.37
    နိုင်ငံ
    0.37
    が登場
    0.37
    POSITIVE LOGITS
     가는
    0.45
     gl
    0.43
    AC
    0.40
     AC
    0.40
    SEG
    0.40
     идти
    0.40
     ш
    0.39
     된다
    0.39
     estacion
    0.39
     시설
    0.39
    Act Density 0.005%

    No Known Activations