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

    Neuronpedia

    INDEX
    Explanations

    always

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অনেকে
    0.45
    जनिक
    0.37
    可能性があります
    0.35
    哪些
    0.34
    သေး
    0.34
    lichting
    0.34
    omized
    0.33
    บาง
    0.33
    чности
    0.33
    途中
    0.33
    POSITIVE LOGITS
     always
    3.91
     всегда
    3.55
    always
    3.53
     siempre
    3.52
     sempre
    3.44
     ALWAYS
    3.42
     Always
    3.39
    Always
    3.39
     завжди
    3.31
     selalu
    3.27
    Act Density 0.052%

    No Known Activations