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

    Neuronpedia

    INDEX
    Explanations

    metaph

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Registry
    -0.08
     traffic
    -0.06
     routines
    -0.06
     retreat
    -0.06
     pla
    -0.06
    oment
    -0.06
     work
    -0.06
     phục
    -0.06
     ابتدا
    -0.06
     cavern
    -0.06
    POSITIVE LOGITS
    .sc
    0.07
     ACE
    0.07
    €
    0.07
    'o
    0.06
     enhances
    0.06
     Filed
    0.06
     Imported
    0.06
    =[]
    0.06
    129
    0.06
    -drive
    0.06
    Act Density 0.009%

    No Known Activations