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

    Neuronpedia

    INDEX
    Explanations

    Among Us, Dos patos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     existentes
    0.75
    ار
    0.74
    ０
    0.70
    ان
    0.68
     about
    0.67
     assurer
    0.67
    (
    0.66
     variar
    0.65
     sbParams
    0.65
    х
    0.65
    POSITIVE LOGITS
    ↵
    1.06
    á
    1.01
    ik
    1.00
    im
    0.99
     The
    0.90
    ë
    0.85
    6
    0.84
    ç
    0.80
     A
    0.80
    ﻪ
    0.79
    Act Density 0.000%

    No Known Activations