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

    Neuronpedia

    INDEX
    Explanations

    SIGINT derived from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    十分に
    0.81
    ंसह
    0.76
    が表示
    0.72
     충분
    0.71
    と共に
    0.70
    对其
    0.70
    ichever
    0.68
    colorbar
    0.67
    陪
    0.67
    Reasons
    0.67
    POSITIVE LOGITS
     involves
    3.60
     involve
    3.52
     involving
    2.65
     involved
    2.63
     melibatkan
    2.55
     envolve
    2.48
     entails
    2.30
     relies
    2.25
     revolves
    2.23
    涉及
    2.10
    Act Density 2.483%

    No Known Activations