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

    Neuronpedia

    INDEX
    Explanations

    WITH RECURSIVE CTEs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ْر
    0.50
    嶈
    0.49
    ាង
    0.48
     kül
    0.48
    能够在
    0.48
    ワイト
    0.46
    جو
    0.46
    став
    0.46
    ycle
    0.46
    ప్తి
    0.46
    POSITIVE LOGITS
     coincides
    0.43
     concomitant
    0.43
     valuation
    0.42
     SSD
    0.42
     concussion
    0.42
     assumed
    0.42
     coincided
    0.42
     Cio
    0.42
     flexion
    0.41
     BTU
    0.41
    Act Density 0.003%

    No Known Activations