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

    Neuronpedia

    INDEX
    Explanations

    police

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /navigation
    -0.07
    haus
    -0.06
     standpoint
    -0.06
    春秋
    -0.06
    OS
    -0.06
     bezpieczeństwa
    -0.06
    .alloc
    -0.06
     compens
    -0.06
    .surface
    -0.06
    .background
    -0.06
    POSITIVE LOGITS
    ')['
    0.08
    </
    0.07
     aiding
    0.07
    一系列
    0.07
     rod
    0.07
     SERIES
    0.06
     glare
    0.06
    盖
    0.06
     نقطة
    0.06
     later
    0.06
    Act Density 0.009%

    No Known Activations