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

    Neuronpedia

    INDEX
    Explanations

    exoplanets and habitable zones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    estructura
    0.39
     দৈ
    0.38
     electrostatic
    0.38
     pointwise
    0.38
    기고
    0.38
    团结
    0.37
    吸引
    0.37
     oblik
    0.37
    뭉
    0.37
     visible
    0.37
    POSITIVE LOGITS
     ex
    0.95
     habitable
    0.79
     extras
    0.77
     planet
    0.71
     exo
    0.68
    extras
    0.68
     rocky
    0.67
     Kepler
    0.67
     Extras
    0.66
    ex
    0.65
    Act Density 0.015%

    No Known Activations