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

    Neuronpedia

    INDEX
    Explanations

    male first names followed by surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Keci
    0.53
    vykor
    0.49
    ১২শ
    0.48
    ྥ
    0.46
    LastGen
    0.46
    माष्टमी
    0.45
     Гинд
    0.45
    ৩৮
    0.45
    ৬৫
    0.45
     Gazprom
    0.45
    POSITIVE LOGITS
     C
    0.56
    -
    0.52
    ie
    0.52
     D
    0.51
     M
    0.49
     J
    0.48
     L
    0.48
     W
    0.47
     S
    0.47
     Scott
    0.47
    Act Density 0.010%

    No Known Activations