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

    Neuronpedia

    INDEX
    Explanations

    smallest deployable unit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    様々な
    0.47
     დიდ
    0.47
     ዋና
    0.47
    常常
    0.46
     लांच
    0.46
     stof
    0.45
     চেয়ে
    0.45
    ئو
    0.44
    দৌ
    0.44
     самом
    0.44
    POSITIVE LOGITS
     ஒத்து
    0.41
     woken
    0.40
     Anomal
    0.39
     NYU
    0.38
     Sigma
    0.37
     Pita
    0.37
    acuse
    0.37
     academics
    0.37
     bub
    0.36
     wakes
    0.36
    Act Density 0.000%

    No Known Activations