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

    Neuronpedia

    INDEX
    Explanations

    events, organizations, or systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ૌ
    0.40
    чник
    0.39
     aggrieved
    0.39
     Likes
    0.39
    림
    0.39
     इं
    0.38
    츨
    0.38
    ாரா
    0.37
    霹
    0.36
    pval
    0.36
    POSITIVE LOGITS
    iOS
    0.45
    Crew
    0.40
     iOS
    0.40
     Gar
    0.38
    谦
    0.36
    ドウ
    0.35
    Organiz
    0.35
    Ministry
    0.35
     ساده
    0.35
    DOE
    0.35
    Act Density 0.000%

    No Known Activations