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

    Neuronpedia

    INDEX
    Explanations

    buildings and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.64
    ীয়
    0.53
     in
    0.52
     on
    0.51
    元の
    0.49
     dată
    0.49
     ৪০
    0.49
     ブリヂストン
    0.49
     beds
    0.48
     différences
    0.48
    POSITIVE LOGITS
    т
    0.68
    ت
    0.66
    H
    0.59
    आर
    0.55
    ר
    0.54
    ᱦ
    0.54
    罅
    0.52
    Buildings
    0.52
    ัล
    0.51
    an
    0.50
    Act Density 0.207%

    No Known Activations