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

    Neuronpedia

    INDEX
    Explanations

    this is the paramount phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    すごく
    0.98
     importantly
    0.91
    Important
    0.91
    非常に
    0.89
     tremendously
    0.89
    IMPORTANT
    0.87
     important
    0.83
     enormously
    0.83
     importants
    0.83
     incredibly
    0.80
    POSITIVE LOGITS
     king
    1.51
     King
    1.27
     KING
    1.26
     synonymous
    1.15
     kings
    1.11
     queen
    1.11
     our
    1.05
     vua
    1.04
     poised
    1.00
    King
    1.00
    Act Density 0.392%

    No Known Activations