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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cameras
    -0.07
    Teen
    -0.07
     volupt
    -0.07
     VB
    -0.07
     intermediary
    -0.07
    道
    -0.07
    _Module
    -0.06
     Tro
    -0.06
     Jose
    -0.06
     TRI
    -0.06
    POSITIVE LOGITS
    "];
↵
    0.07
     anthology
    0.07
    ]);
↵
    0.06
    로드
    0.06
     hayır
    0.06
    =h
    0.06
     angered
    0.06
    ocols
    0.06
    ]))
↵
    0.06
     mentally
    0.06
    Act Density 0.014%

    No Known Activations