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

    Neuronpedia

    INDEX
    Explanations

    indirect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ']:
    0.52
    מו
    0.48
     современном
    0.47
    "]:
    0.46
    closures
    0.46
    ’:
    0.46
    FindingsRequest
    0.46
    志
    0.45
     божомолдору
    0.45
    说什么
    0.45
    POSITIVE LOGITS
    ↵↵
    0.60
     Additionally
    0.53
    ↵↵↵
    0.50
     Fakt
    0.49
     tatsächlich
    0.49
     garn
    0.47
    、「
    0.47
     rémun
    0.47
    ↵
    0.47
     Komb
    0.47
    Act Density 0.004%

    No Known Activations