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

    Neuronpedia

    INDEX
    Explanations

    dimensions and measurements like height and weight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pumps
    1.02
     harnesses
    0.87
     stickers
    0.86
     suction
    0.85
     zippers
    0.84
     temperature
    0.83
     holiday
    0.82
     headlights
    0.81
     magnification
    0.80
     straps
    0.80
    POSITIVE LOGITS
    гент
    0.83
     Woolf
    0.82
     advogado
    0.82
     Provincia
    0.81
    ेंटल
    0.76
    Usuario
    0.76
    クトル
    0.76
    Sidebar
    0.75
    igeons
    0.75
    utat
    0.74
    Act Density 0.035%

    No Known Activations