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

    Neuronpedia

    INDEX
    Explanations

    suffering and pain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    3.28
    িক
    3.13
     choses
    2.92
    त्मक
    2.90
     randomIndex
    2.89
    na
    2.82
    ル
    2.81
    zers
    2.77
     wszystkim
    2.72
    ்களை
    2.71
    POSITIVE LOGITS
    ו
    4.36
    ে
    3.34
    days
    3.03
    o
    2.81
    iciency
    2.79
    ettu
    2.79
    আবার
    2.74
    سون
    2.73
    ೆ
    2.72
    ా
    2.66
    Act Density 0.029%

    No Known Activations