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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Button
    -0.08
    	height
    -0.08
    Heavy
    -0.07
    Field
    -0.07
     rotation
    -0.07
    Label
    -0.07
     py
    -0.07
    Joe
    -0.07
     bearings
    -0.07
     head
    -0.07
    POSITIVE LOGITS
     us
    0.13
     Us
    0.09
     UNS
    0.08
    Us
    0.08
     UCS
    0.08
    AS
    0.07
     urlencode
    0.07
    .us
    0.07
    asu
    0.07
    \uB
    0.07
    Act Density 0.027%

    No Known Activations