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

    Neuronpedia

    INDEX
    Explanations

    conspiracy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gradu
    -0.08
     progressivement
    -0.08
    车型
    -0.08
     ifade
    -0.08
     диск
    -0.07
    	spin
    -0.07
     brightest
    -0.07
     MUCH
    -0.07
     untersucht
    -0.07
     bras
    -0.07
    POSITIVE LOGITS
    犯罪
    0.09
     verniet
    0.09
     murder
    0.09
     öld
    0.08
     synerg
    0.08
     thereto
    0.08
    召开
    0.08
    ợp
    0.08
     wrongdoing
    0.08
     agreements
    0.08
    Act Density 0.004%

    No Known Activations