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

    Neuronpedia

    INDEX
    Explanations

    consideration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FRE
    -0.07
     foll
    -0.07
    -awesome
    -0.06
    stripe
    -0.06
    ijn
    -0.06
    ?type
    -0.06
    uges
    -0.06
     Excellence
    -0.06
    /print
    -0.06
     Picasso
    -0.06
    POSITIVE LOGITS
     investigates
    0.07
     TWO
    0.07
     FOUR
    0.07
     principals
    0.06
     Residential
    0.06
    commons
    0.06
    ″E
    0.06
    سبب
    0.06
     restoring
    0.06
     sulf
    0.06
    Act Density 0.006%

    No Known Activations