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

    Neuronpedia

    INDEX
    Explanations

    human resources or HR

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۔
    0.82
    는
    0.75
    是
    0.68
     siphon
    0.59
    '
    0.56
     కే
    0.54
     ನಿಮ್ಮ
    0.53
    '،
    0.53
     smartphone
    0.52
    。
    0.51
    POSITIVE LOGITS
    T
    0.76
    B
    0.63
    Payroll
    0.61
    Muchas
    0.61
    ты
    0.59
    Pupp
    0.59
    t
    0.58
    el
    0.58
    difficulty
    0.56
    ̣t
    0.56
    Act Density 0.006%

    No Known Activations