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

    Neuronpedia

    INDEX
    Explanations

    physics. data. guide. who. manufacturer. document

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Motivation
    0.46
     zeal
    0.45
    EUR
    0.44
    er
    0.43
    langan
    0.43
     europ
    0.43
     )
    0.40
    Reason
    0.40
    jets
    0.40
     der
    0.39
    POSITIVE LOGITS
    牷
    0.57
    روی
    0.55
    㖵
    0.54
    浿
    0.53
     thoracique
    0.53
     fréquence
    0.52
    艐
    0.52
    .\\
    0.49
    پ
    0.49
    ਸ
    0.49
    Act Density 0.001%

    No Known Activations