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

    Neuronpedia

    INDEX
    Explanations

    non-English words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     referral
    0.51
     refinance
    0.49
     cartridge
    0.48
     randomly
    0.47
     referrer
    0.47
     get
    0.47
     individually
    0.46
     referee
    0.46
    0.46
     competitively
    0.46
    POSITIVE LOGITS
    労働
    0.56
     राउत
    0.49
    犍
    0.49
     шум
    0.48
     урок
    0.47
    淦
    0.47
     мэ
    0.47
     број
    0.47
     உருவாக்கி
    0.46
    SOI
    0.46
    Act Density 0.000%

    No Known Activations