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

    Neuronpedia

    INDEX
    Explanations

    methodology and theorems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _NAME
    -0.07
     lst
    -0.07
     Theta
    -0.07
    .lst
    -0.06
    ],↵
    -0.06
     transmitter
    -0.06
     Guide
    -0.06
     respondents
    -0.06
     مجموعه
    -0.06
     Depot
    -0.06
    POSITIVE LOGITS
     GestureDetector
    0.07
    ระบ
    0.07
     přísluš
    0.07
     nächsten
    0.07
    韩
    0.06
     bloody
    0.06
    compute
    0.06
     ژاپ
    0.06
     поп
    0.06
    .Feature
    0.06
    Act Density 0.035%

    No Known Activations