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

    Neuronpedia

    INDEX
    Explanations

    geopolitical entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    0.46
    ו
    0.43
    ется
    0.42
    cwnd
    0.41
     Héctor
    0.41
    wxyz
    0.39
    йся
    0.39
     हालांकि
    0.39
     ткань
    0.38
    ब्ल्यू
    0.38
    POSITIVE LOGITS
    .
    0.38
     avven
    0.37
    ren
    0.35
    ning
    0.32
    B
    0.31
    ');
    0.30
    otros
    0.30
    ｲ
    0.30
     Revisited
    0.30
     sanctuaries
    0.29
    Act Density 0.231%

    No Known Activations