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

    Neuronpedia

    INDEX
    Explanations

    itself every

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waarmee
    0.50
    ્લા
    0.46
     постара
    0.46
     смерти
    0.44
    ва
    0.43
    йте
    0.43
    ás
    0.43
     взаимодействия
    0.43
     которыми
    0.42
     zm
    0.42
    POSITIVE LOGITS
    ش
    0.44
     ゴルフ
    0.44
     haci
    0.43
     USO
    0.43
    aping
    0.42
     music
    0.41
    several
    0.41
     actors
    0.41
    inim
    0.41
     কেবল
    0.40
    Act Density 0.001%

    No Known Activations