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

    Neuronpedia

    INDEX
    Explanations

    illicit information gathering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Matches
    -0.09
    estones
    -0.08
    telegram
    -0.08
     중국
    -0.08
     sterker
    -0.08
    hanga
    -0.08
     avec
    -0.08
    PHONE
    -0.08
    堵
    -0.08
     Со
    -0.08
    POSITIVE LOGITS
    —even
    0.09
     ordinarily
    0.08
     unofficial
    0.08
     officiële
    0.08
     lernen
    0.08
    并
    0.08
     intellectual
    0.08
     circumvent
    0.08
     offiziellen
    0.08
     disreg
    0.07
    Act Density 0.021%

    No Known Activations