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

    Neuronpedia

    INDEX
    Explanations

    ocracy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conducive
    -0.08
     cou
    -0.07
     Bird
    -0.07
     chest
    -0.07
     killings
    -0.07
     wrist
    -0.06
     transferring
    -0.06
     einz
    -0.06
     forfe
    -0.06
     collectors
    -0.06
    POSITIVE LOGITS
     democracy
    0.08
     Democracy
    0.08
    .
↵
    0.07
    Epoch
    0.07
    )
↵
↵
    0.07
     DECL
    0.07
     democr
    0.06
     democratic
    0.06
    َ
    0.06
     Process
    0.06
    Act Density 0.007%

    No Known Activations