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

    Neuronpedia

    INDEX
    Explanations

    technical labels and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     長
    0.57
     knapp
    0.57
     stanov
    0.55
    ↵↵↵↵↵↵↵↵
    0.54
    ↵↵↵↵↵↵↵↵↵↵
    0.52
     refug
    0.49
    i
    0.49
     vä
    0.48
     耐
    0.48
     atleta
    0.48
    POSITIVE LOGITS
    সভার
    0.45
     Samaritan
    0.44
    را
    0.43
    arin
    0.43
    elfth
    0.42
    ो
    0.42
    ດ້ວຍ
    0.42
    ở
    0.42
    ༥
    0.42
    Fone
    0.42
    Act Density 0.000%

    No Known Activations