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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    click
    -0.07
     Thái
    -0.07
     요청
    -0.06
     Você
    -0.06
    ::*
    -0.06
     mejores
    -0.06
     atmosphere
    -0.06
    нання
    -0.06
     bathrooms
    -0.06
    doing
    -0.06
    POSITIVE LOGITS
     슈
    0.06
     อำเภ
    0.06
    プ
    0.06
    aptic
    0.06
    (--
    0.06
     MPS
    0.06
    )\<
    0.06
     Ή
    0.06
     �
    0.06
     sire
    0.06
    Act Density 0.043%

    No Known Activations