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

    Neuronpedia

    INDEX
    Explanations

    geographical place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ныгы
    0.47
    मॉडल
    0.44
     renderings
    0.41
     जाइए
    0.40
     oxígeno
    0.39
     کاروبار
    0.39
    Ắ
    0.39
     apasion
    0.39
     amenable
    0.38
     جذاب
    0.38
    POSITIVE LOGITS
     Deutschland
    0.38
     Suisse
    0.37
     Universo
    0.37
    缇
    0.37
     Roma
    0.37
     Rum
    0.37
     Switzerland
    0.37
     Hessen
    0.36
     Ritual
    0.36
     Stiftung
    0.36
    Act Density 0.000%

    No Known Activations