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

    Neuronpedia

    INDEX
    Explanations

    places and geography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     জিজ্ঞ
    0.62
     civilization
    0.54
     अकेला
    0.50
    ÔNG
    0.50
    grond
    0.50
     scenery
    0.49
     Civilization
    0.49
     civilized
    0.49
    ᾷ
    0.49
     collectiv
    0.47
    POSITIVE LOGITS
    et
    0.63
    an
    0.59
    on
    0.57
    o
    0.57
    lot
    0.50
    ನ
    0.49
    lar
    0.49
    lay
    0.49
    nuclear
    0.48
    lab
    0.48
    Act Density 0.000%

    No Known Activations