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

    Neuronpedia

    INDEX
    Explanations

    reducing negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    1.89
    नों
    1.84
    𝘳
    1.79
    \$
    1.77
    𝘮
    1.71
    রাও
    1.70
    𝘺
    1.70
     والمع
    1.64
    𝘵
    1.64
    र
    1.57
    POSITIVE LOGITS
     $(<
    2.05
     thiểu
    1.79
     charla
    1.67
    ↓↓
    1.61
    ्युनिटी
    1.57
    àu
    1.51
     совсем
    1.51
    1.51
     thiệu
    1.50
    Proposition
    1.49
    Act Density 0.264%

    No Known Activations