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

    Neuronpedia

    INDEX
    Explanations

    film critics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sensors
    -0.07
    .ViewGroup
    -0.07
     airline
    -0.06
     довольно
    -0.06
     cited
    -0.06
     shaft
    -0.06
     však
    -0.06
     --------
    -0.06
    (cc
    -0.06
    ==========
    -0.06
    POSITIVE LOGITS
     رفع
    0.06
     Popular
    0.06
     multipart
    0.06
    que
    0.06
     زر
    0.06
     země
    0.06
     organiz
    0.06
     putt
    0.06
     αρχ
    0.06
     ποι
    0.06
    Act Density 0.006%

    No Known Activations