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

    Neuronpedia

    INDEX
    Explanations

    microwave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    0.99
    ies
    0.97
     in
    0.89
    1
    0.84
    é
    0.82
    w
    0.82
    ia
    0.81
    á
    0.81
    st
    0.81
    ie
    0.81
    POSITIVE LOGITS
    انية
    0.74
     textBox
    0.72
    rụ
    0.72
    ジー
    0.71
    食べた
    0.68
    водится
    0.67
    ージ
    0.67
     yapılan
    0.67
    FontFace
    0.67
    ր
    0.66
    Act Density 0.001%

    No Known Activations