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

    Neuronpedia

    INDEX
    Explanations

    Herr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Acad
    -0.07
    sınız
    -0.07
     existence
    -0.06
    .Dimension
    -0.06
     todas
    -0.06
     begun
    -0.06
    323
    -0.06
     society
    -0.06
     Carlo
    -0.06
     SRC
    -0.06
    POSITIVE LOGITS
     Kerr
    0.08
    nelle
    0.07
     Cooking
    0.07
    .kernel
    0.07
    .preference
    0.07
    ierce
    0.07
    err
    0.07
    -к
    0.07
    uns
    0.07
     Hull
    0.07
    Act Density 0.005%

    No Known Activations