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

    Neuronpedia

    INDEX
    Explanations

    pollutants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obedient
    -0.08
     recycle
    -0.07
    EMPL
    -0.07
    	gbc
    -0.07
    ackBar
    -0.07
     مشار
    -0.06
     roof
    -0.06
     traces
    -0.06
    .setSize
    -0.06
    -era
    -0.06
    POSITIVE LOGITS
     pollutants
    0.13
     contaminants
    0.08
    nt
    0.07
     constituent
    0.07
     Unix
    0.07
     Till
    0.07
     pollut
    0.06
     Collins
    0.06
    614
    0.06
    ปร
    0.06
    Act Density 0.004%

    No Known Activations