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

    Neuronpedia

    INDEX
    Explanations

    travel cards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gum
    0.44
     picnic
    0.44
    驾驶
    0.41
     aiutare
    0.40
     motorbike
    0.40
     tf
    0.39
    িত্ব
    0.38
     помощь
    0.38
    特別
    0.38
     specie
    0.38
    POSITIVE LOGITS
    }\|^
    0.49
     Италия
    0.39
    лект
    0.39
    κρα
    0.39
     Italiana
    0.37
     conveys
    0.36
    ім
    0.36
    Observ
    0.36
    ração
    0.36
    Windows
    0.35
    Act Density 0.000%

    No Known Activations