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

    Neuronpedia

    INDEX
    Explanations

    referencing previously stated information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     عاش
    0.41
     Gem
    0.41
     স্থাপিত
    0.40
     Aces
    0.40
     overlying
    0.40
     overclock
    0.40
     Tun
    0.39
     üzerinden
    0.39
     Dukes
    0.39
    淼
    0.39
    POSITIVE LOGITS
     herein
    0.79
     earlier
    0.64
     therein
    0.59
     ранее
    0.58
     выше
    0.52
     далее
    0.51
     anteriormente
    0.51
     sebelumnya
    0.50
    previously
    0.50
     précédemment
    0.50
    Act Density 0.015%

    No Known Activations