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

    Neuronpedia

    INDEX
    Explanations

    _image

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ży
    -0.07
    cliffe
    -0.07
    版权归
    -0.07
     Publi
    -0.07
    锼
    -0.06
    갃
    -0.06
     alarmed
    -0.06
    ﭧ
    -0.06
    ﻝ
    -0.06
    赇
    -0.06
    POSITIVE LOGITS
    Backend
    0.08
     �
    0.07
     efficient
    0.07
     concaten
    0.07
    这一
    0.07
    Opening
    0.07
    	mode
    0.07
    ibration
    0.07
    container
    0.07
    เจ
    0.07
    Act Density 0.001%

    No Known Activations