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

    Neuronpedia

    INDEX
    Explanations

    find or identify or install

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngo
    0.50
    러
    0.50
    emos
    0.49
    ota
    0.49
    ote
    0.48
    ety
    0.47
    oti
    0.47
    uctive
    0.46
    鍰
    0.46
    angnya
    0.46
    POSITIVE LOGITS
    िंग
    0.60
    ال
    0.55
    
    0.53
    ار
    0.52
     quán
    0.49
    pués
    0.48
    िक्स
    0.48
    ು
    0.47
     প্রকাশিত
    0.46
    ंसिल
    0.46
    Act Density 0.006%

    No Known Activations