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

    Neuronpedia

    INDEX
    Explanations

    other alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     addirittura
    0.49
     zelfs
    0.49
    <0x95>
    0.46
     sogenannten
    0.45
     Anche
    0.44
     குறிப்பாக
    0.44
     маленький
    0.42
    同時に
    0.41
     Даже
    0.41
    ಲ್ಲೂ
    0.41
    POSITIVE LOGITS
     other
    1.78
     अन्य
    1.69
     অন্যান্য
    1.67
     других
    1.63
    其他
    1.56
     autres
    1.55
     інших
    1.52
     otras
    1.51
    その他の
    1.51
     andere
    1.48
    Act Density 0.237%

    No Known Activations