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

    Neuronpedia

    INDEX
    Explanations

    computed or reactivity signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     milioni
    0.52
    ali
    0.50
    Interface
    0.50
     למ
    0.50
    एल
    0.50
     מק
    0.50
    irit
    0.50
     한
    0.50
     กัน
    0.49
    ί
    0.49
    POSITIVE LOGITS
    цей
    0.53
    ведения
    0.51
     szere
    0.51
    ष्ठा
    0.50
    प्रदेश
    0.50
    вою
    0.50
    ೊಂಡ
    0.50
    ップ
    0.49
     Goode
    0.49
    перыі
    0.49
    Act Density 0.001%

    No Known Activations