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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    럽
    -0.07
     �
    -0.07
     Conversely
    -0.07
     kot
    -0.06
     نتیجه
    -0.06
    Mapper
    -0.06
     Fields
    -0.06
    QUE
    -0.06
    оч
    -0.06
     sense
    -0.06
    POSITIVE LOGITS
    (gca
    0.07
    �인
    0.07
     万円
    0.06
    film
    0.06
    _FIRE
    0.06
    (filter
    0.06
    .CON
    0.06
    .Microsoft
    0.06
    ίνει
    0.06
     сал
    0.06
    Act Density 0.166%

    No Known Activations