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

    Neuronpedia

    INDEX
    Explanations

    Artemis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    having
    -0.08
    opers
    -0.08
    existent
    -0.08
     рай
    -0.08
     zen
    -0.08
     tác
    -0.08
    .const
    -0.07
    	scale
    -0.07
    Having
    -0.07
     impact
    -0.07
    POSITIVE LOGITS
     Bones
    0.09
     merry
    0.08
     invigor
    0.08
     revital
    0.08
     joga
    0.08
    组
    0.08
     Hole
    0.08
     menstru
    0.08
     gusta
    0.07
     mara
    0.07
    Act Density 0.001%

    No Known Activations