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

    Neuronpedia

    INDEX
    Explanations

    on connect, on tick, on close

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    學者
    0.39
    谨慎
    0.38
    槛
    0.37
    的海
    0.37
    细腻
    0.37
     Lakeside
    0.36
    घु
    0.36
     Dioxide
    0.35
     Gründe
    0.35
    쏙
    0.35
    POSITIVE LOGITS
     وعلى
    1.12
     behalf
    1.00
     základě
    0.59
     باندې
    0.53
     basis
    0.51
     occasion
    0.51
     occasions
    0.48
     निर्भर
    0.46
    的基础上
    0.44
     was
    0.43
    Act Density 0.012%

    No Known Activations