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

    Neuronpedia

    INDEX
    Explanations

    implementing and executing strategies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.51
     និង
    0.51
     và
    0.48
     ਅਤੇ
    0.48
     आणि
    0.47
     And
    0.46
     మరియు
    0.46
     कर्मी
    0.45
     և
    0.44
     եւ
    0.44
    POSITIVE LOGITS
     unei
    0.48
    य
    0.47
     unui
    0.44
    सू
    0.42
     sebuah
    0.42
    ח
    0.40
    एक
    0.40
    ɥ
    0.40
     politič
    0.40
    ट
    0.39
    Act Density 0.021%

    No Known Activations