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

    Neuronpedia

    INDEX
    Explanations

    planetary systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ansch
    0.52
     নির্ভ
    0.49
     linie
    0.47
     Schein
    0.44
     держави
    0.44
    皑
    0.42
     πα
    0.42
     роди
    0.41
     чор
    0.41
     rank
    0.41
    POSITIVE LOGITS
    大臣
    0.49
    읍
    0.46
    a
    0.45
    記者
    0.45
    ముఖ
    0.45
     Joseph
    0.45
    説
    0.45
    সম্যান
    0.44
    navigationLinks
    0.44
    ため
    0.43
    Act Density 0.007%

    No Known Activations