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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    本
    -0.07
     پرو
    -0.07
     дви
    -0.07
     dưới
    -0.06
     Aqu
    -0.06
    セン
    -0.06
    �
    -0.06
    (segment
    -0.06
     Sesso
    -0.06
    sending
    -0.06
    POSITIVE LOGITS
     creditors
    0.07
    Secret
    0.06
     SAFE
    0.06
     conexao
    0.06
     Unique
    0.06
    печ
    0.06
    (STD
    0.06
     stage
    0.06
     исключ
    0.06
    (Time
    0.06
    Act Density 0.021%

    No Known Activations