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

    Neuronpedia

    INDEX
    Explanations

    political and social concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bullpen
    0.40
    وار
    0.39
     hardware
    0.36
     س
    0.34
     است
    0.34
     Safe
    0.34
     ا
    0.34
     interfaces
    0.34
     Gallows
    0.33
     on
    0.33
    POSITIVE LOGITS
     истори
    0.41
    jahteraan
    0.40
     విజ
    0.40
    শ্বরের
    0.39
     POLITICAL
    0.39
    riks
    0.38
     полити
    0.38
    InnerText
    0.38
     carinatis
    0.37
    сал
    0.37
    Act Density 0.379%

    No Known Activations