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

    Neuronpedia

    INDEX
    Explanations

    a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ারণ
    0.42
     detonations
    0.42
     frequency
    0.42
     frequencies
    0.41
     AZ
    0.40
    参见
    0.40
     anomaly
    0.39
    frequencies
    0.38
     explosion
    0.38
     freq
    0.38
    POSITIVE LOGITS
    ത്ത
    0.42
    торию
    0.36
     प्र
    0.36
    ichtigung
    0.35
    водство
    0.35
    0.35
    ψει
    0.35
     चेक
    0.35
     Subsequently
    0.35
    <0xE3>
    0.34
    Act Density 0.000%

    No Known Activations