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

    Neuronpedia

    INDEX
    Explanations

    own life, libreria, trade wars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вопро
    0.42
    시킨
    0.40
     tentang
    0.38
     કામ
    0.38
     पा
    0.38
     postfix
    0.36
     aspekt
    0.36
     вопросы
    0.36
     ပဲ
    0.36
     கலந்து
    0.36
    POSITIVE LOGITS
    player
    0.45
    hooter
    0.43
    Brewer
    0.43
    Players
    0.42
     brewer
    0.42
    Dry
    0.41
     splatter
    0.41
    SPL
    0.40
    퓰
    0.40
    Cost
    0.40
    Act Density 0.000%

    No Known Activations