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

    Neuronpedia

    INDEX
    Explanations

    many or numerous others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     godfather
    0.45
     goalkeeper
    0.44
     antiga
    0.43
     Ahab
    0.41
     Stef
    0.40
     بالإضافة
    0.40
     ብቻ
    0.39
     Filho
    0.39
     antigo
    0.39
     தோட்டங்கள்
    0.39
    POSITIVE LOGITS
    ）
    0.51
    }
    0.45
    \
    0.45
    र्ष
    0.43
    0
    0.42
    ロ
    0.42
    =
    0.41
    ар
    0.40
    +
    0.40
    üler
    0.39
    Act Density 0.002%

    No Known Activations