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

    Neuronpedia

    INDEX
    Explanations

    None

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imation
    0.72
     clears
    0.70
     Northwest
    0.67
     symptom
    0.66
     northwest
    0.66
     credit
    0.65
     inertial
    0.65
     upload
    0.65
     statistic
    0.65
     frames
    0.64
    POSITIVE LOGITS
    None
    0.78
    Т
    0.76
    一个
    0.74
    Бо
    0.73
    R
    0.68
    Ꭲ
    0.67
    Ther
    0.65
    Ли
    0.63
    W
    0.63
    Х
    0.63
    Act Density 0.109%

    No Known Activations