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

    Neuronpedia

    INDEX
    Explanations

    scientific studies/trials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    вався
    -0.07
    илися
    -0.06
    countries
    -0.06
     викон
    -0.06
     ∀
    -0.06
    anchise
    -0.06
    Fire
    -0.06
     людям
    -0.06
     cud
    -0.06
    _numer
    -0.06
    POSITIVE LOGITS
    %%
    0.07
    καν
    0.07
     dislike
    0.07
     еж
    0.06
     самостоятель
    0.06
     Shaft
    0.06
     sights
    0.06
    ัมพ
    0.06
     лист
    0.06
     Panda
    0.06
    Act Density 0.191%

    No Known Activations