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

    Neuronpedia

    INDEX
    Explanations

    cinema with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mun
    1.05
     Sable
    0.96
     Ros
    0.89
     Mun
    0.89
     Cros
    0.89
    Castro
    0.88
     Sant
    0.87
     Booth
    0.86
    sgn
    0.85
    Ros
    0.85
    POSITIVE LOGITS
     MVC
    0.98
     Hickory
    0.90
     atrium
    0.89
     ZIP
    0.88
    boxylic
    0.88
    icarboxylic
    0.86
    icted
    0.86
     collection
    0.85
    igenza
    0.85
     alpine
    0.84
    Act Density 0.563%

    No Known Activations