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

    Neuronpedia

    INDEX
    Explanations

    comprehensive breakdowns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     slightly
    0.41
     niektórych
    0.40
     merely
    0.39
     occasionally
    0.38
    ését
    0.38
     একটু
    0.37
    uuuu
    0.37
     Bila
    0.36
     luck
    0.36
     essence
    0.36
    POSITIVE LOGITS
     comprehensively
    0.55
     umfass
    0.48
     советы
    0.47
    Method
    0.46
     종합
    0.45
     comprehensive
    0.44
    howto
    0.43
    Approach
    0.42
    涵盖
    0.42
    综合
    0.42
    Act Density 0.014%

    No Known Activations