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

    Neuronpedia

    INDEX
    Explanations

    make you feel/think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ATIONS
    0.41
     Friends
    0.40
    用户的
    0.40
    IEF
    0.40
     memastikan
    0.38
     دوستان
    0.38
    imų
    0.38
    变成了
    0.38
    amos
    0.38
     жиз
    0.38
    POSITIVE LOGITS
     me
    0.46
     us
    0.43
     задума
    0.43
    బి
    0.41
    statement
    0.41
     quir
    0.40
    Statement
    0.39
     jaws
    0.39
     pensare
    0.37
     heads
    0.37
    Act Density 0.014%

    No Known Activations