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

    Neuronpedia

    INDEX
    Explanations

    replace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Admin
    -0.08
     stirring
    -0.07
    Markers
    -0.07
     minut
    -0.07
    	no
    -0.07
    utr
    -0.07
     authenticated
    -0.07
    trial
    -0.06
     surgeons
    -0.06
     subtly
    -0.06
    POSITIVE LOGITS
     replacing
    0.10
     replacements
    0.10
     replacement
    0.09
    Replace
    0.09
     replace
    0.09
     replaced
    0.09
     Replace
    0.08
    Replacement
    0.08
     Replacement
    0.07
     rebuild
    0.07
    Act Density 0.024%

    No Known Activations