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

    Neuronpedia

    INDEX
    Explanations

    foundational concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    สามารถ
    0.51
     สามารถ
    0.46
    directly
    0.42
    ability
    0.39
    /
    0.39
    currently
    0.39
    possibly
    0.38
     pouvant
    0.38
     nearest
    0.38
    可能性があります
    0.38
    POSITIVE LOGITS
     galore
    0.54
     чемпи
    0.53
     Matters
    0.49
     Comes
    0.49
     fateful
    0.48
     Surprisingly
    0.47
     chàng
    0.47
     சிதம்ப
    0.46
     ngunit
    0.46
     lakini
    0.44
    Act Density 0.039%

    No Known Activations