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

    Neuronpedia

    INDEX
    Explanations

    income, price, arrest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     धार
    0.40
     Congrès
    0.39
    คว
    0.38
     exemplaire
    0.38
    ït
    0.38
    émy
    0.38
    狧
    0.37
     methanol
    0.37
    $'
    0.37
    ্লাই
    0.37
    POSITIVE LOGITS
    信心
    0.44
    ৷
    0.43
     साइज
    0.43
    &)
    0.38
    0.37
     क्यो
    0.36
    ረጥ
    0.35
     استعداد
    0.34
     عام
    0.33
     தேர்த
    0.33
    Act Density 0.000%

    No Known Activations