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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Order
    -0.07
     civilization
    -0.07
    inition
    -0.07
    ��
    -0.06
    south
    -0.06
     disguised
    -0.06
     mex
    -0.06
     Germ
    -0.06
    .insert
    -0.06
    ля
    -0.06
    POSITIVE LOGITS
    _pc
    0.07
    Impro
    0.06
    _DEPEND
    0.06
    Bid
    0.06
     saya
    0.06
    Người
    0.06
     köln
    0.06
    -login
    0.06
    .LAZY
    0.06
    -inc
    0.06
    Act Density 0.052%

    No Known Activations