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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     urine
    -0.07
    	ps
    -0.07
     yani
    -0.07
     rast
    -0.06
     melting
    -0.06
     fingerprints
    -0.06
     placements
    -0.06
    fil
    -0.06
     enslaved
    -0.06
    dehy
    -0.06
    POSITIVE LOGITS
    (Role
    0.07
     lỗi
    0.07
    时
    0.06
    _LOOKUP
    0.06
    HomeController
    0.06
     POSIX
    0.06
     Fog
    0.06
     Ces
    0.06
     Taş
    0.06
       ↵    ↵
    0.06
    Act Density 0.011%

    No Known Activations