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

    Neuronpedia

    INDEX
    Explanations

    enabling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indign
    0.33
     murderous
    0.33
     assassinated
    0.33
     infuri
    0.32
     humiliating
    0.31
     REALLY
    0.31
     bew
    0.30
     horribly
    0.30
     utter
    0.29
     murió
    0.29
    POSITIVE LOGITS
     สามารถ
    0.40
     предоставляет
    0.39
    provides
    0.38
     provides
    0.38
    สามารถ
    0.38
     Furthermore
    0.38
     Provides
    0.37
    Provides
    0.37
     Allows
    0.37
     Additionally
    0.35
    Act Density 0.043%

    No Known Activations