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

    Neuronpedia

    INDEX
    Explanations

    interior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mitch
    -0.07
    	open
    -0.07
    UDGE
    -0.07
    .available
    -0.06
    Mitch
    -0.06
    Even
    -0.06
    —even
    -0.06
     pushes
    -0.06
    _link
    -0.06
     Gene
    -0.06
    POSITIVE LOGITS
     interior
    0.12
    Interior
    0.10
     exterior
    0.09
     Interior
    0.09
     interiors
    0.08
    II
    0.08
    roof
    0.08
    rear
    0.08
     tors
    0.08
     IV
    0.08
    Act Density 0.009%

    No Known Activations