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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    viders
    -0.06
     зрозум
    -0.06
     JsonRequest
    -0.06
    AVE
    -0.06
     porque
    -0.06
    ้องพ
    -0.06
    ��
    -0.06
     RW
    -0.06
     meer
    -0.06
    POSITIVE LOGITS
     quân
    0.06
    phony
    0.06
     fifo
    0.06
    κρα
    0.06
    del
    0.06
     Οικο
    0.06
    том
    0.06
    �
    0.06
    pcl
    0.06
    .Token
    0.06
    Act Density 0.224%

    No Known Activations