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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    excluding
    -0.06
     OA
    -0.06
    iples
    -0.06
     SYN
    -0.06
     Ms
    -0.06
    luent
    -0.06
    дан
    -0.06
     nurturing
    -0.06
    avou
    -0.05
    	X
    -0.05
    POSITIVE LOGITS
    äge
    0.07
    ğü
    0.07
    (constants
    0.06
     と
    0.06
     ห
    0.06
     Each
    0.06
    .body
    0.06
    ()._
    0.06
     being
    0.06
     AppConfig
    0.06
    Act Density 0.058%

    No Known Activations