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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     samples
    -0.08
    keiten
    -0.07
    ROP
    -0.07
     deficit
    -0.06
    іє
    -0.06
    фика
    -0.06
    alten
    -0.06
     vedení
    -0.06
     aras
    -0.06
     něho
    -0.06
    POSITIVE LOGITS
     gris
    0.07
     Creation
    0.07
    -used
    0.07
     Typeface
    0.07
     Highland
    0.07
    ż
    0.06
     foregoing
    0.06
     THC
    0.06
     rms
    0.06
     erkek
    0.06
    Act Density 0.018%

    No Known Activations