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

    Neuronpedia

    INDEX
    Explanations

    and generate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مند
    0.44
     Brigitte
    0.39
    ெழு
    0.36
    Brig
    0.36
    াস্থ্য
    0.36
    ভূত
    0.36
     Brig
    0.35
    ම්භ
    0.35
     Van
    0.35
     inmate
    0.35
    POSITIVE LOGITS
    дэ
    0.37
    <unused11>
    0.36
    0.36
    chsler
    0.35
    0.35
    RealPath
    0.34
    鱸
    0.34
    リアル
    0.33
     معاملہ
    0.33
    นะครับ
    0.33
    Act Density 0.005%

    No Known Activations