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

    Neuronpedia

    INDEX
    Explanations

    focus on the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gambling
    0.63
     investment
    0.57
     Qatar
    0.57
     accounting
    0.57
     offshoring
    0.57
     Accounting
    0.55
     트
    0.55
    㴬
    0.55
     ocean
    0.54
     Nikki
    0.54
    POSITIVE LOGITS
    ين
    0.77
    ية
    0.73
    ου
    0.73
     konzent
    0.71
     concentrate
    0.69
     somente
    0.68
    IN
    0.62
     Concentrate
    0.61
     concent
    0.60
    ă
    0.60
    Act Density 0.170%

    No Known Activations