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

    Neuronpedia

    INDEX
    Explanations

    handling threats or problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    QS
    0.75
    勇气
    0.74
    ws
    0.73
     quotients
    0.73
    Ws
    0.72
     Quotient
    0.72
    няется
    0.72
    QUIN
    0.71
     minuten
    0.70
    WS
    0.70
    POSITIVE LOGITS
     peacekeeping
    0.77
    具体的
    0.70
     badly
    0.69
     পাঠক
    0.69
    彼此
    0.68
    掉
    0.67
     clear
    0.67
     chế
    0.66
    手的
    0.66
    笞
    0.65
    Act Density 0.003%

    No Known Activations