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

    Neuronpedia

    INDEX
    Explanations

    election, fraction, traditional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     поме
    0.45
    ندن
    0.43
     தொற்று
    0.39
    bingen
    0.38
     !”
    0.36
     pinn
    0.36
    希
    0.36
    腐
    0.35
     एवरीवन
    0.35
    旎
    0.35
    POSITIVE LOGITS
    }",
    0.40
    orio
    0.38
    ^(
    0.38
    Thay
    0.38
     aprove
    0.37
    /<
    0.37
    ]'
    0.37
    tham
    0.36
     Miet
    0.36
     instantiation
    0.36
    Act Density 0.001%

    No Known Activations