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

    Neuronpedia

    INDEX
    Explanations

    Inter intermediary interruption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    轸
    0.43
    鍚
    0.38
    尌
    0.38
    栯
    0.37
     கிஷோர்
    0.36
     সমিতি
    0.35
    ्रू
    0.34
    迺
    0.34
    ्यास
    0.33
    ęć
    0.33
    POSITIVE LOGITS
     Inter
    4.09
    Inter
    4.03
    inter
    3.78
     интер
    3.72
     inter
    3.70
     INTER
    3.64
    INTER
    3.53
     인터
    3.45
     інтер
    3.44
     इंटर
    3.42
    Act Density 0.165%

    No Known Activations