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

    Neuronpedia

    INDEX
    Explanations

    Text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    анні
    -0.07
     Loads
    -0.07
    誉
    -0.07
    321
    -0.06
     Colum
    -0.06
     مركز
    -0.06
     Enlightenment
    -0.06
    ��
    -0.06
    �
    -0.06
    loom
    -0.06
    POSITIVE LOGITS
    ,color
    0.07
    	opts
    0.06
     Pelosi
    0.06
     kys
    0.06
    ofile
    0.06
     فل
    0.06
     Ging
    0.06
    Love
    0.06
     Website
    0.06
     LAB
    0.06
    Act Density 0.000%

    No Known Activations