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

    Neuronpedia

    INDEX
    Explanations

    Lagrange

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fres
    -0.09
    lut
    -0.09
    мит
    -0.08
     Jahres
    -0.08
     আক্রান্ত
    -0.08
     einger
    -0.08
    aranja
    -0.07
     excepc
    -0.07
    感染
    -0.07
     certainty
    -0.07
    POSITIVE LOGITS
    骚
    0.08
     Scouts
    0.07
     BETWEEN
    0.07
    دين
    0.07
     Historically
    0.07
    _RAM
    0.07
    RAM
    0.07
     Trabalho
    0.07
     Tell
    0.07
     rhetoric
    0.07
    Act Density 0.001%

    No Known Activations