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

    Neuronpedia

    INDEX
    Explanations

    expresses degrees of importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    1.09
     for
    0.96
     on
    0.94
    两种
    0.88
    ుల
    0.84
     are
    0.83
     as
    0.79
     SCO
    0.79
     to
    0.77
    ®,
    0.77
    POSITIVE LOGITS
     commencer
    0.97
    èrent
    0.90
     recordar
    0.88
     parecía
    0.88
     quería
    0.88
    欲しい
    0.87
     puedes
    0.86
    収入
    0.86
     commander
    0.85
     encuentre
    0.84
    Act Density 0.270%

    No Known Activations