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

    Neuronpedia

    INDEX
    Explanations

    opposed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rentals
    -0.07
     clay
    -0.07
     recovered
    -0.06
    321
    -0.06
     earned
    -0.06
    	holder
    -0.06
     Fast
    -0.06
     rn
    -0.06
     rit
    -0.06
     Healthy
    -0.06
    POSITIVE LOGITS
    Opp
    0.09
     oppose
    0.08
     opposition
    0.08
     Opp
    0.07
    UP
    0.07
     Pap
    0.07
     opponent
    0.07
    FormsModule
    0.07
     division
    0.07
    �
    0.07
    Act Density 0.013%

    No Known Activations