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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pek
    -0.06
     sensations
    -0.06
    itious
    -0.06
    ={`${
    -0.05
     maxim
    -0.05
     FINAL
    -0.05
     emergencies
    -0.05
    /
↵
↵
    -0.05
     Garmin
    -0.05
     kapas
    -0.05
    POSITIVE LOGITS
     include
    0.07
     Conv
    0.07
    ически
    0.07
    	op
    0.07
     urge
    0.07
     hr
    0.07
    Grupo
    0.07
    netinet
    0.07
    ule
    0.07
    ύν
    0.07
    Act Density 0.027%

    No Known Activations