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

    Neuronpedia

    INDEX
    Explanations

    groups of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     .
    0.24
    ۔
    0.22
    。
    0.21
     passant
    0.21
     fives
    0.21
     iOS
    0.20
     Serif
    0.20
    мб
    0.20
     five
    0.20
     Erit
    0.20
    POSITIVE LOGITS
    也都
    0.30
     flocked
    0.29
     đều
    0.26
     collectively
    0.26
     unanimously
    0.26
     applauded
    0.25
    纷纷
    0.24
     eagerly
    0.24
     anxiously
    0.24
    議論
    0.24
    Act Density 0.104%

    No Known Activations