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

    Neuronpedia

    INDEX
    Explanations

    food items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Monitoring
    0.50
     Evaluation
    0.48
     Pengembangan
    0.48
     Monitoring
    0.47
     sifatida
    0.47
    투
    0.47
     aggreg
    0.46
     Maximum
    0.46
    Maximum
    0.46
    림
    0.46
    POSITIVE LOGITS
     cakes
    0.68
    㭜
    0.66
     sillas
    0.66
    clothes
    0.65
     телефона
    0.64
     brownies
    0.64
     tortillas
    0.63
    łeś
    0.63
     doughnuts
    0.63
     slippers
    0.62
    Act Density 0.008%

    No Known Activations