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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Restr
    -0.07
    偏
    -0.07
     McCoy
    -0.07
     saturated
    -0.07
     sanitation
    -0.06
     สำน
    -0.06
     Restrictions
    -0.06
    .Transaction
    -0.06
    579
    -0.06
    =event
    -0.06
    POSITIVE LOGITS
     adjoining
    0.07
     out
    0.06
    ot
    0.06
     nell
    0.06
     cigar
    0.06
    shortcut
    0.06
     phút
    0.06
     battled
    0.06
     cipher
    0.06
    enal
    0.06
    Act Density 0.000%

    No Known Activations