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

    Neuronpedia

    INDEX
    Explanations

    OWNER

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dar
    -0.08
     fascinating
    -0.07
    萋
    -0.07
     billeder
    -0.07
    ﯙ
    -0.07
    	glog
    -0.06
     '~
    -0.06
    얏
    -0.06
    iggins
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    面部
    0.08
     readability
    0.08
    读者
    0.07
    霉
    0.07
    ado
    0.07
    Gender
    0.07
    recht
    0.07
    	ob
    0.07
    _CUDA
    0.07
     TERMIN
    0.07
    Act Density 0.001%

    No Known Activations