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

    Neuronpedia

    INDEX
    Explanations

    cd followed by project name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onds
    0.68
    体力
    0.63
    strass
    0.62
     વ્યવ
    0.61
    ეცი
    0.59
     දක්
    0.58
     famil
    0.58
    nite
    0.58
    xssf
    0.58
    ennis
    0.57
    POSITIVE LOGITS
     धु
    0.75
     Pseudomonas
    0.72
     phải
    0.70
     только
    0.70
    煨
    0.70
    เท่านั้น
    0.68
     आधिकारिक
    0.67
     migliore
    0.67
     inaccurate
    0.67
    ওই
    0.66
    Act Density 0.003%

    No Known Activations