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

    Neuronpedia

    INDEX
    Explanations

    reversing text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nazy
    0.34
    νου
    0.33
    ஸ்ட
    0.31
     pirate
    0.30
    ව්
    0.29
     nightclub
    0.29
    の本
    0.29
     främ
    0.29
    '.
    0.29
    скому
    0.29
    POSITIVE LOGITS
    very
    0.44
    Very
    0.42
    非常に
    0.42
     very
    0.41
     വളരെ
    0.40
     हैं
    0.40
     somewhat
    0.38
     весьма
    0.38
     હોય
    0.37
     છે
    0.37
    Act Density 0.000%

    No Known Activations