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

    Neuronpedia

    INDEX
    Explanations

    skip or return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ֿ
    0.44
     бед
    0.41
     discretized
    0.40
    Serializable
    0.39
    ㄍ
    0.38
     سەر
    0.38
    на
    0.38
    ак
    0.38
    כת
    0.37
    тен
    0.37
    POSITIVE LOGITS
     Skip
    0.76
     不需要
    0.75
     skip
    0.74
     already
    0.69
     skipping
    0.69
     Already
    0.68
    無需
    0.68
    skip
    0.66
     Skipping
    0.66
     SKIP
    0.64
    Act Density 0.120%

    No Known Activations