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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    онт
    -0.08
    atch
    -0.08
     européen
    -0.08
    /js
    -0.07
     предостав
    -0.07
     размер
    -0.07
     deserialize
    -0.07
    atisch
    -0.07
     trivial
    -0.07
    ameleon
    -0.07
    POSITIVE LOGITS
    が多く
    0.07
    遵义
    0.07
    international
    0.07
     연구
    0.06
     הללו
    0.06
    ₨
    0.06
    榄
    0.06
    鄢
    0.06
    &W
    0.06
    LD
    0.06
    Act Density 0.000%

    No Known Activations