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

    Neuronpedia

    INDEX
    Explanations

    interest and expense

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     měla
    0.83
    ણે
    0.78
    Franc
    0.72
    Corporate
    0.71
    incredible
    0.71
    େ
    0.71
    aires
    0.70
     से
    0.70
     Кор
    0.69
    Ang
    0.69
    POSITIVE LOGITS
    人物
    0.70
     चतुर्थी
    0.68
     productId
    0.66
     pulleys
    0.63
     nhiêu
    0.63
     Ions
    0.63
     piloting
    0.62
     hauling
    0.61
     Charge
    0.61
     Trio
    0.61
    Act Density 0.003%

    No Known Activations